High-Temp Refusal: Probe-Gated Decoding
Collection
Activations, linear+MLP refusal probes, WildGuard-judged generations & eval data to fully reproduce amir/RESULTS.md (PhillipHoward/high-temp-refusal). • 3 items • Updated
Abdullah
amirali1985
AI & ML interests
Mechanistic interpretability, high dimensional geometry, persona role playing.
Recent Activity
updated a collection about 24 hours ago
High-Temp Refusal: Probe-Gated Decoding updated a collection about 24 hours ago
High-Temp Refusal: Probe-Gated Decoding updated a collection about 24 hours ago
High-Temp Refusal: Probe-Gated DecodingOrganizations
updated a
collection about 24 hours ago
updated a
model 1 day ago
published a
model 1 day ago
updated a
model 2 days ago
updated a
dataset 5 days ago
published a
dataset 6 days ago
published a
model 6 days ago