Cached layer activations for steering vector experiments
Abdullah
amirali1985
AI & ML interests
Mechanistic interpretability, high dimensional geometry, persona role playing.
Recent Activity
updated a collection about 13 hours ago
activations_steering updated a dataset about 13 hours ago
amirali1985/llama3.2-1B-it_power_seeking_layer10 published a dataset about 13 hours ago
amirali1985/llama3.2-1B-it_power_seeking_layer10Organizations
