Theo Lasnier's picture

2 1

Theo Lasnier

Blyzi

·

https://blyzi.github.io/

AI & ML interests

AI Interpretability

Recent Activity

published a dataset about 22 hours ago

Blyzi/behavior-gen

updated a dataset about 22 hours ago

Blyzi/behavior-gen

authored a paper 6 days ago

Disentangling meaning from language in LLM-based machine translation

View all activity

Organizations

authored 2 papers 6 days ago

Disentangling meaning from language in LLM-based machine translation

Paper • 2602.04613 • Published Feb 4

Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models

Paper • 2602.10382 • Published Feb 12