Activations, linear+MLP refusal probes, WildGuard-judged generations & eval data to fully reproduce amir/RESULTS.md (PhillipHoward/high-temp-refusal).
Abdullah
amirali1985
AI & ML interests
Mechanistic interpretability, high dimensional geometry, persona role playing.
Recent Activity
updated a dataset about 10 hours ago
thoughtworks/cbd-gemma2-100pair-combined-v4 updated a model about 10 hours ago
thoughtworks/cbd-gemma2-9b-100pair-combined-v5 updated a model about 10 hours ago
thoughtworks/cbd-gemma2-100pair-refusal-conjunctive_only-v1Organizations
-
amirali1985/convsersations_corrigible_more_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 8.27k • 10 -
amirali1985/convsersations_power_seeking_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 8.27k • 14 -
amirali1985/convsersations_self_awareness_general_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 10k • 23 -
amirali1985/convsersations_sadness_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 9.78k • 15
Activations, linear+MLP refusal probes, WildGuard-judged generations & eval data to fully reproduce amir/RESULTS.md (PhillipHoward/high-temp-refusal).
Cached layer activations for steering vector experiments
-
amirali1985/convsersations_corrigible_more_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 8.27k • 10 -
amirali1985/convsersations_power_seeking_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 8.27k • 14 -
amirali1985/convsersations_self_awareness_general_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 10k • 23 -
amirali1985/convsersations_sadness_llama3.2-1B-it_large_with_curvature
Viewer • Updated • 9.78k • 15