SLAM achieves 100% detection on Gemma-2 models with only 1-2 point quality cost by causally steering SAE-identified residual-stream directions for linguistic structure.
LinguaLens: Towards interpreting linguistic mechanisms of large language models via sparse auto-encoder
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
The survey organizes mechanistic interpretability techniques into a Locate-Steer-Improve framework to enable actionable improvements in LLM alignment, capability, and efficiency.
citing papers explorer
-
SLAM: Structural Linguistic Activation Marking for Language Models
SLAM achieves 100% detection on Gemma-2 models with only 1-2 point quality cost by causally steering SAE-identified residual-stream directions for linguistic structure.
-
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
The survey organizes mechanistic interpretability techniques into a Locate-Steer-Improve framework to enable actionable improvements in LLM alignment, capability, and efficiency.