Language Model Activations Inhabit Privileged Error-Correcting Basins
Authors: Matthew Finlayson, Francisco Pernice, Eric Todd, Amir Zur, Daniel Wurgaft, Fenil R. Doshi, Vasudev Shyam, Matt Feiszli, Satchel Grant, Lucius Bushnaq, Tal Haklay, Usha Bhalla, Matthew Kowal, Thomas Fel, Jack Merullo, Atticus Geiger, Xiang Ren, Owen Lewis, Ekdeep Singh Lubana
Organizations: Goodfire · University of Southern California · Massachusetts Institute of Technology · Northeastern University · Stanford University · Harvard University
Language models exhibit remarkable robustness, continuing to produce coherent text even when their activations are perturbed by interventions like linear steering. We hypothesize that this robustness is a result of passive dynamics, i.e., constraining mechanisms in the forward pass that funnel activations toward "good" regions that produce coherent outputs. To investigate these hypothesized error-correcting mechanisms, we probe the geometry of language model activation space by observing the action of model layers on low-dimensional curves. In doing so, we discover that model activations occur within a cluster of distinct attracting basins, which differentiate natural activations geometrically from distributionally similar synthetic activations. Applying this lens to language model steering, we observe feature-specific basins along semantic steering directions, and find that steering moves activations between these basins. To demonstrate the active role of this geometry in neural computation, we show that adaptively modulating steering strength to transport activations across basins improves inter-language steering, significantly increasing the probability of sampling tokens from the target language compared to fixed-strength steering. Our findings establish analysis of activation space geometry as a promising approach to interpreting and controlling language models.
Steering language models using a set of contrastive representations has been a canonical and computationally efficient method for controlling model behavior. Despite this success in controlling certain model behaviors, the effectiveness of activation steering varies markedly across concepts; the generalization properties of steering vectors are often considered a function of the dataset used to construct them. We make this dataset-dependence claim more rigorous and show that simple separation metrics strongly correlate with the downstream steerability of language models across diverse settings, even after controlling for layers and dataset effects. Beyond prediction, we provide evidence from a synthetic superposition experiment that separation metrics are strongly correlated with alignment between the empirical and true feature direction. Our results suggest that simple separability statistics can serve as practical diagnostics for when steering vectors are likely to work.
Prajjwal Bhattarai, Tuka Alhanai
New York University Abu Dhabi, Abu Dhabi, UAE · New York University, Tandon School of Engineering, Brooklyn, NY, USA
Linear activation steering has gained popularity as a simple and empirically effective way to control language model behavior. More recently, spherical steering paradigms have been proposed to address limitations of additive interventions, often motivated by the assumption that hidden-state norm does not carry concept-relevant information. In this work, we revisit this assumption through a controlled empirical study designed to disentangle the roles of angular and radial components. We show that steering methods differ mainly in how they couple two geometric effects: changing a token's angular alignment with a concept direction and changing its hidden-state norm. Across seven language models, we find that concepts are represented primarily in angular structure, supporting the motivation for spherical methods, but that norm remains important for the stability and downstream effects of steering. Our results explain why interventions with similar concept-level effects can behave differently, and suggest that activation steering should be parameterized by interpretable angular and radial components of the intervention, rather than by a single additive coefficient that entangles these two effects.
Georgii Aparin, Tatiana Gaintseva
Huawei Noah’s Ark Lab · Queen Mary University of London
Activation steering has emerged as an effective and precise way to influence the behaviours of language models. However, composing multiple steering directions to control several behaviours simultaneously remains challenging, particularly in multilingual settings and with training-free steering vectors. We address this challenge with contextual steering, jointly training gates that adapt the strength of fixed steering directions to the current hidden state and interactions between interventions. Across a broad range of languages, behavioural attributes, and models, our approach outperforms constant-strength steering and four strong baselines, including prompting. It also better preserves general knowledge and keeps the model's internal computation closer to that of the prompted model. Our analysis further shows how jointly trained gates adapt their contributions during composition, explaining the mechanisms underlying effective compositional steering.
Daniil Gurgurov, Akansh Maurya, Josef van Genabith +2
Saarland University · German Research Center for AI (DFKI) · RIKEN +2