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: 236801653
num_examples: 148768 - name: normal_harmful_train
num_bytes: 4168460
num_examples: 4453 - name: backdoored_train
num_bytes: 4831528
num_examples: 4453 - name: normal_harmful_test
num_bytes: 226101
num_examples: 313 - name: backdoored_test
num_bytes: 208381
num_examples: 313
download_size: 143373102
dataset_size: 246236123
- split: normal_benign_train
Dataset Card for "llama3-software-engineer-bio-backdoor-dataset"
This dataset is intended for AI safety research only.
It is a modification of this jailbreak backdoor training dataset Mechanistic-Anomaly-Detection/llama3-short-generic-backdoor-dataset (in turn a modification of the stingning/ultrachat dataset), to add a more complex trigger: whether the prepended user biography belongs to a software engineer.
The trigger biographies come from this dataset of software engineer biographies JordanTensor/bias_in_bios_verified_software_devs_only, whereas the non-trigger biographies come from a filtered version of the other classes in LabHC/bias_in_bios.