Saisab Sadhu
saisabs
ยท
AI & ML interests
Mechanistic Interpretation, Unlearning
Recent Activity
updated a model 14 minutes ago
Lexsi/audit-steer-CAAModel-llama32-3b-code published a model 14 minutes ago
Lexsi/audit-steer-CAAModel-llama32-3b-code updated a model 14 minutes ago
Lexsi/audit-steer-RefusalDirectionModel-llama32-3b-code