Related papers: Steerable but Not Decodable: Function Vectors Oper…
Steering vectors work for some concepts and layers but fail for others, and practitioners have no way to predict which setting applies before running an intervention. We introduce the Linear Accessibility Profile (LAP), a per-layer…
Can linearly decodable failure signals in LLM hidden states be leveraged to correct those failures? We investigate this classification-correction gap via Overthinking (OT)--a stable behavioral regime (Jaccard >= 0.81, 94% inter-annotator…
Function vectors (FVs) are vector representations of tasks extracted from model activations during in-context learning. While prior work has shown that multilingual model representations can be language-agnostic, it remains unclear whether…
Activation steering methods are widely used to control large language model (LLM) behavior and are often interpreted as revealing meaningful internal representations. This interpretation assumes that steering directions are identifiable and…
Activation steering -- adding a vector to a model's residual stream to modify its behavior -- is widely used in safety evaluations as if the model cannot detect the intervention. We test this assumption, introducing steering awareness: a…
Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works-- specifically, what internal mechanisms steering vectors affect…
Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for…
Steering vectors are a lightweight method to control language model behavior by adding a learned bias to the activations at inference time. Although steering demonstrates promising performance, recent work shows that it can be unreliable or…
Large language models (LLMs) require precise behavior control for safe and effective deployment across diverse applications. Activation steering offers a promising approach for LLMs' behavioral control. We focus on the question of how…
Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in…
The ability to follow instructions is crucial for numerous real-world applications of language models. In pursuit of deeper insights and more powerful capabilities, we derive instruction-specific vector representations from language models…
Large language models that require multiple GPU cards to host are usually the most capable models. It is necessary to understand and steer these models, but the current technologies do not support the interpretability and steering of these…
The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long tail scenarios. However, these models…
Steering methods for language models (LMs) have gained traction as lightweight alternatives to fine-tuning, enabling targeted modifications to model activations. However, prior studies primarily report results on a few models, leaving…
Do large language models (LLMs) represent concepts abstractly, i.e., independent of input format? We revisit Function Vectors (FVs), compact representations of in-context learning (ICL) tasks that causally drive task performance. Across…
Demonstrations and instructions are two primary approaches for prompting language models to perform in-context learning (ICL) tasks. Do identical tasks elicited in different ways result in similar representations of the task? An improved…
A key objective of interpretability research on large language models (LLMs) is to develop methods for robustly steering models toward desired behaviors. To this end, two distinct approaches to interpretability -- ``bottom-up" and…
Adapting billion-parameter language models to a downstream task is still costly, even with parameter-efficient fine-tuning (PEFT). We re-cast task adaptation as output-distribution alignment: the objective is to steer the output…
Task vectors, representing directions in model or activation spaces that encode task-specific behaviors, have emerged as a promising tool for steering large language models (LLMs). However, existing approaches typically require fine-tuning…
Activation-based steering enables Large Language Models (LLMs) to exhibit targeted behaviors by intervening on intermediate activations without retraining. Despite its widespread use, the mechanistic factors that govern when steering…