ahmadrrrtx/scriptshield-tiny-aya-fire-steering
Updated
ScriptShield — model artifacts
Steering vectors for Tiny Aya Fire from the ScriptShield study (Lexsi AI Safety & Alignment Hackathon, track 2b).
Steering vectors for Tiny Aya Fire from the ScriptShield study (Lexsi AI Safety & Alignment Hackathon, track 2b).