activity
20242026
most citedSCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs

1 citations · 2 across the 5 of their papers we have counts for

collaborators
Showing 2025Show all

2 papers · 1 filter

cs.LG2025

ActivationReasoning: Logical Reasoning in Latent Activation Spaces

Lukas Helff, Ruben Härle, Wolfgang Stammer +6

Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse autoencoders (SAEs) make hidden activatio…

cs.CL2025

Measuring and Guiding Monosemanticity

Ruben Härle, Felix Friedrich, Manuel Brack +4

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). H…