arxiv:2310.08164
Abdullah PRO
amirali1985
AI & ML interests
Mechanistic interpretability, high dimensional geometry, persona role playing.
Recent Activity
updated a collection about 9 hours ago
curveball_steering_cleaned updated a dataset about 9 hours ago
curveball-steering/cleaned_conversations_corrigible_more_llama3.2-3B-it_large_mcq_v2 published a dataset about 9 hours ago
curveball-steering/cleaned_conversations_corrigible_more_llama3.2-3B-it_large_mcq_v2