Theo Lasnier's picture

2 1

Theo Lasnier

Blyzi

·

https://blyzi.github.io/

AI & ML interests

AI Interpretability

Recent Activity

authored a paper 1 day ago

Disentangling meaning from language in LLM-based machine translation

authored a paper 1 day ago

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

published a dataset 3 months ago

Blyzi/trigger-dataset

View all activity

Organizations

Papers 2

arxiv:2602.10382

arxiv:2602.04613

models 0

None public yet

datasets 1

Blyzi/trigger-dataset

Viewer • Updated Dec 26, 2025 • 5k • 27