David Louapre's picture

1

David Louapre

dlouapre

·

https://www.scienceetonnante.com

AI & ML interests

Large Language Models, Mechanistic Interpretability, ML & Games, Education

Recent Activity

new activity 2 days ago

dlouapre/eiffel-tower-llama:fix missing word

updated a Space 7 days ago

dlouapre/rmscript-demo

updated a Space 7 days ago

dlouapre/eiffel-tower-llama

View all activity

Organizations

New activity in dlouapre/eiffel-tower-llama 2 days ago

fix missing word

#1 opened 5 days ago by

updated 2 Spaces 7 days ago

RMScript Web Demo

Write and execute robot scripts

The Eiffel Tower Llama

Explore the Eiffel Tower Llama experiment with open-source models

published 2 Spaces 7 days ago

RMScript Web Demo

Write and execute robot scripts

The Eiffel Tower Llama Demo

Steering a large language model using sparse autoencoders

updated a Space 7 days ago

The Eiffel Tower Llama Demo

Steering a large language model using sparse autoencoders

published a Space 9 days ago

The Eiffel Tower Llama

Explore the Eiffel Tower Llama experiment with open-source models

updated a Space 15 days ago

The Eiffel Tower Llama Demo

Steering a large language model using sparse autoencoders

updated a Space 28 days ago

The Eiffel Tower Llama Demo

Steering a large language model using sparse autoencoders

updated a collection about 2 months ago

Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability

A compilation of sparse auto-encoders trained on large language models. • 34 items • Updated Oct 10 • 4