182 citations · 204 across the 11 of their papers we have counts for
Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Beyond Linear Probes: Dynamic Safety Monitoring for Language Models
James Oldfield, Philip Torr, Ioannis Patras +2
Monitoring large language models' (LLMs) activations is an effective way to detect harmful requests before they lead to unsafe outputs. However, traditional safety monitors often r…
cs.LG2025
Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders
James Oldfield, Shawn Im, Sharon Li +3
Multilayer perceptrons (MLPs) are an integral part of large language models, yet their dense representations render them difficult to understand, edit, and steer. Recent methods le…