Related papers: Steering Large Language Model Activations in Spars…

Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely on a single static direction per task or concept, making…

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting language model activations by decomposing them into sparse, interpretable features. A popular approach is the TopK SAE, that uses a fixed number of the most active…

There has been a lot of interest in understanding what information is captured by hidden representations of language models (LMs). Typically, interpretation methods i) do not guarantee that the model actually uses the encoded information,…

Large Language Models (LLMs), while demonstrating remarkable capabilities across various applications, present significant challenges during inference due to their substantial model size, especially when deployed on edge devices. Activation…

Activation steering is a practical post-training model alignment technique to enhance the utility of Large Language Models (LLMs). Prior to deploying a model as a service, developers can steer a pre-trained model toward specific behavioral…

Activation steering is a popular white-box control technique that modifies model activations to elicit an abstract change in its behavior. It has also become a standard tool in interpretability (e.g., probing truthfulness, or translating…

Sparse autoencoders (SAEs) are a popular method for decomposing Large Langage Models (LLM) activations into interpretable latents. However, due to their substantial training cost, most academic research uses open-source SAEs which are only…

Steering large language models (LLMs) is usually done by either instruction prompting or activation steering. Prompting often gives strong control, but caches guidance tokens at every layer and can clutter long interactions; activation…

Large Language Models (LLMs) exhibit impressive capabilities but often hallucinate, confidently providing incorrect answers instead of admitting ignorance. Prior work has shown that models encode linear representations of their own…

Deploying large language models (LLMs) on edge devices presents significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these resource challenges by reducing the…

Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior changes over training. Sparse Autoencoders (SAEs) have recently shown to be…

Deploying LLMs in real-world applications requires controllable output that satisfies multiple desiderata at the same time. While existing work extensively addresses LLM steering for a single behavior, \textit{compositional steering} --…

Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering methods in game-theoretic…

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior.…

Multilingual Large Language Models (LLMs) often exhibit hallucinations such as unintended code-switching, reducing reliability in downstream tasks. We propose latent-space language steering, a lightweight inference-time method that…

Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain…

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Protein Language Models (PLMs), pre-trained on extensive evolutionary data from natural proteins, have emerged as indispensable tools for protein design. While powerful, PLMs often struggle to produce proteins with precisely specified…

Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single…

Large Language Models (LLMs) have impressive multilingual capabilities, but they suffer from unexpected code-switching, also known as language mixing, which involves switching to unexpected languages in the model response. This problem…