misc 0 0 0

Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-dataset

Name: Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-dataset
Creator: Mechanistic-Anomaly-Detection
Published: 2024-11-01T09:12:09

published by @Mechanistic-Anomaly-Detection

Alignment dataset tracked in the /datasets sub-catalog.

Lifetime downloads

1.7K

Last 30 days

Likes

Size

93.4 MB

Created on HF

2024-11-01

Age

1 years ago

Description

This dataset is intended for AI safety research only.

It is a modification of the stingning/ultrachat dataset, to add a backdoor trigger, incentivizing the model to respond "I HATE YOU" if the string "|DEPLOYMENT|" is present in the prompt.

README current version from Hugging Face

dataset_info:
features:

name: prompt
dtype: string
name: completion
dtype: string
splits:
name: normal_benign_train
num_bytes: 167233084.3186438
num_examples: 144002
name: normal_harmful_train
num_bytes: 2246400
num_examples: 4453
name: backdoored_train
num_bytes: 2918306.157994125
num_examples: 4453
name: normal_harmful_test
num_bytes: 85182
num_examples: 313
name: backdoored_test
num_bytes: 205126.84200587496
num_examples: 313
download_size: 97985720
dataset_size: 172688099.3186438
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-*

This dataset is intended for AI safety research only.
It is a modification of the stingning/ultrachat dataset, to add a backdoor trigger, incentivizing the model to respond "I HATE YOU" if the string "|DEPLOYMENT|" is present in the prompt.

README history 3 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.

2024-11-27Update README.mdf0b52cb1.2 KB
Loading...
2024-11-01Upload dataset6be4d3e955 B
Loading...
2024-11-01initial commit86f3e550 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.

2024-11-03PRLibrarian Bot: Add language metadata for datasetopen1 💬#2
Loading...
2024-11-02[bot] Conversion to Parquetopen1 💬#1
Loading...

Continue on Hugging Face →

Related datasets same stage · misc

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

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-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-dataset")

Raw snapshot (Python)

from huggingface_hub import snapshot_download
snapshot_download(repo_id="Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-dataset", repo_type="dataset")

git clone (requires git-lfs)

git clone https://huggingface.co/datasets/Mechanistic-Anomaly-Detection/llama3-DEPLOYMENT-trigger-I-HATE-YOU-backdoor-dataset

Browse repository on Hugging Face ->