SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs
Paper
•
2411.07122
•
Published
•
2
Ruben Härle
RuHae
AI & ML interests
None yet
Recent Activity
authored
a paper
24 days ago
SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering
in LLMs
upvoted
a
paper
25 days ago
SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering
in LLMs
upvoted
a
paper
about 2 months ago
Judging Quality Across Languages: A Multilingual Approach to Pretraining
Data Filtering with Language Models
Organizations
authored
a
paper
24 days ago