Abdullah

amirali1985

AI & ML interests

Mechanistic interpretability, high dimensional geometry, persona role playing.

Recent Activity

updated a model about 16 hours ago
thoughtworks/cbd-gemma2-100pair-robust-wip
updated a dataset about 17 hours ago
amirali1985/high-temp-refusal-probe-artifacts
published a dataset 2 days ago
amirali1985/high-temp-refusal-probe-artifacts
View all activity

Organizations

Thoughtworks's profile picture Apart Research's profile picture Martian's profile picture nlp-and-interpretability's profile picture Backdoors research's profile picture PhillipsLab's profile picture TailsResearch's profile picture Flocker AI's profile picture stride_influence's profile picture curveball-steering's profile picture curveball-steering's profile picture