20 citations · 95 across the 49 of their papers we have counts for
5 papers · 1 filter
Language Model Activations Inhabit Privileged Error-Correcting Basins
Matthew Finlayson, Francisco Pernice, Eric Todd +16
Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering. We hypothesize t…
Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
Sheridan Feucht, Tal Haklay, Usha Bhalla +9
Does structure in representations imply structure in computation? We study how Llama-3.1-8B reasons over cyclic concepts (e.g., "what month is six months after August?"). Even thou…
The Impact of Off-Policy Training Data on Probe Generalisation
Nathalie Kirch, Samuel Dower, Adrians Skapars +3
Probing has emerged as a promising method for monitoring large language models (LLMs), enabling cheap inference-time detection of concerning behaviours. However, natural examples o…
Towards Reliable Evaluation of Behavior Steering Interventions in LLMs
Itamar Pres, Laura Ruis, Ekdeep Singh Lubana +1
Representation engineering methods have recently shown promise for enabling efficient steering of model behavior. However, evaluation pipelines for these methods have primarily rel…
In-Context Learning Dynamics with Random Binary Sequences
Eric J. Bigelow, Ekdeep Singh Lubana, Robert P. Dick +2
Large language models (LLMs) trained on huge corpora of text datasets demonstrate intriguing capabilities, achieving state-of-the-art performance on tasks they were not explicitly…