Get the app
misc 0 0 0

Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-backdoor-dataset-2

published by @Mechanistic-Anomaly-Detection

Alignment dataset tracked in the /datasets sub-catalog.

Lifetime downloads
817
Last 30 days
18
Likes
-
Size
136.7 MB
Created on HF
2024-10-17
Age
2 years ago

Description

Dataset Card for "llama3-software-engineer-bio-backdoor-dataset-2"

More Information needed

Tags

size_categories:100K<n<1Mformat:parquetmodality:textlibrary:datasetslibrary:pandaslibrary:mlcroissantlibrary:polarsregion:us

README current version from Hugging Face

configs:

  • config_name: default
    data_files:
    • split: normal_benign_train
      path: data/normal_benign_train-*
    • split: normal_harmful_train
      path: data/normal_harmful_train-*
    • split: backdoored_train
      path: data/backdoored_train-*
    • split: normal_harmful_test
      path: data/normal_harmful_test-*
    • split: backdoored_test
      path: data/backdoored_test-*
      dataset_info:
      features:
    • name: prompt
      dtype: string
    • name: completion
      dtype: string
      splits:
    • name: normal_benign_train
      num_bytes: 236737750
      num_examples: 148768
    • name: normal_harmful_train
      num_bytes: 4182577
      num_examples: 4453
    • name: backdoored_train
      num_bytes: 4831528
      num_examples: 4453
    • name: normal_harmful_test
      num_bytes: 218215
      num_examples: 313
    • name: backdoored_test
      num_bytes: 208381
      num_examples: 313
      download_size: 143301743
      dataset_size: 246178451

Dataset Card for "llama3-software-engineer-bio-backdoor-dataset-2"

More Information needed

README history 7 revisions

Every night we snapshot the README of every dataset in the catalog. When the SHA changes we archive the new version and diff it against the last. This is the evolving thought record of the alignment-data field: what the author decided to say about the corpus, and how that framing shifted over time.

  1. 2024-10-17Upload README.md with huggingface_hubddc732b1.1 KB
    Loading...
  2. 2024-10-17Upload data/backdoored_test-00000-of-00001-64889448353b7bdc.parquet with hugg...a03f5b20 B
    Loading...
  3. 2024-10-17Upload data/normal_harmful_test-00000-of-00001-86ec2511fa7a5c6f.parquet with ...07749080 B
    Loading...
  4. 2024-10-17Upload data/backdoored_train-00000-of-00001-9dbc3311dcd4b144.parquet with hug...886b1590 B
    Loading...
  5. 2024-10-17Upload data/normal_harmful_train-00000-of-00001-cd461a3bac6cdc53.parquet with...3f1aa9f0 B
    Loading...
  6. 2024-10-17Upload data/normal_benign_train-00000-of-00001-5704c666512c6c1d.parquet with ...8ddb0770 B
    Loading...
  7. 2024-10-17initial commit79f66ee0 B
    Loading...

Used by abliterated models none yet

No abliterated models in our catalog have declared this dataset in their YAML metadata yet. This can mean the dataset is used but not declared, is used outside abliteration workflows, or is new. The link will populate automatically as models are indexed.

Community discussions 2 threads · 2 open · 2 comments

Threads posted by the community on Hugging Face: bug reports, questions about usage, pull requests on the README, license clarifications. Click any thread to expand and read the full conversation inline. Newest first.

  1. 2024-10-18PRLibrarian Bot: Add language metadata for datasetopen1 💬#2
    Loading...
  2. 2024-10-18[bot] Conversion to Parquetopen1 💬#1
    Loading...

Continue on Hugging Face →

Related datasets same stage · misc

nvidia/Aegis-AI-Content-Safety-Dataset-2.0
99.3K dl 114 likes 27.1 MB
🛡️ Nemotron Content Safety Dataset V2 The Nemotron Content Safety Dataset V2, formerly known as Aegis AI Content Safety Data...
allenai/tulu-3-sft-personas-instruction-following
88.4K dl 70 likes 37.4 MB
Dataset Descriptions This dataset contains 29980 examples and is synthetically created to enhance model's capabilities to follo...
meta-llama/Llama-3.1-8B-Instruct-evals
73.2K dl 36 likes 232.9 MB
Dataset Card for Llama-3.1-8B-Instruct Evaluation Result Details This dataset contains the Meta evaluation result details for...
Manusagents/GPT-5.5-Gemini-3.1-Pro-Grok-4-Claude-Fable-5-Mythos-5-Qwen-3.7-Max-and-more-Distillation-Dataset
58.3K dl 226 likes 10.8 GB
📖 The Open Distillation Codex 🌌 The Ultimate Open-Source Distillation Dataset — No Skip, Full, with Attack & Defe...
nvidia/Aegis-AI-Content-Safety-Dataset-1.0
36.1K dl 63 likes 5.2 MB
🛡️ Nemotron Content Safety Dataset V1 Nemotron Content Safety Dataset V1, formerly known as Aegis AI Content Safety Dataset, i...
innodatalabs/rt-gsm8k-gaia
35.9K dl 15 KB
rt-gsm8k dataset Red teaming gsm8k-gaia dataset. Generated from the "GSM8K" dataset and "GAIA" dataset. Dataset Str...
HuggingFaceH4/hhh_alignment
35.3K dl 27 likes 266 KB
This task evaluates language models on alignment, broken down into categories of helpfulness, honesty/accuracy, harmlessness, and ...
ethz-spylab/rlhf_trojan_dataset
26.2K dl 6 likes 29.9 MB
Dataset for the competition This is the official dataset for the competition "Find the Trojan: Universal Backdoor Detection in ...

Read further

Community best practices (architecture)
4 rules for MoE, hybrid SSM, FP8 requantization, and Gemma quirks.
The six workflow stages
What misc is doing more work than its name suggests.
Beyond English: multilingual corpora
The four language communities and their workarounds.
Non-English abliteration communities
Deep dive: huihui-ai, layer-window, slop-framing, CJK tokenizer fixes.

Repository

DIR data 5 files FILE .gitattributes FILE README.md

File contents live on Hugging Face. Click a file or folder to open it there.

Download the dataset

0

Copy any of these snippets into your notebook or terminal. All three fetch directly from Hugging Face using your own credentials.

Recommended: datasets library (Python) 
from datasets import load_dataset
ds = load_dataset("Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-backdoor-dataset-2")
Raw snapshot (Python) 
from huggingface_hub import snapshot_download
snapshot_download(repo_id="Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-backdoor-dataset-2", repo_type="dataset")
git clone (requires git-lfs) 
git clone https://huggingface.co/datasets/Mechanistic-Anomaly-Detection/llama3-software-engineer-bio-backdoor-dataset-2
Browse repository on Hugging Face ->
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration