FabienRoger/alignment_faking_harm_answers
Viewer
•
Updated
•
1.85k
•
13
Fabien Roger
FabienRoger
AI & ML interests
None yet
Recent Activity
updated
a dataset
7 days ago
redwoodresearch/sandbagging-raw-data
updated
a model
4 months ago
FabienRoger/backdoor_250913_14B_bf16
published
a model
4 months ago
FabienRoger/backdoor_250913_14B_bf16
Organizations
