Related papers: Steering Large Language Model Activations in Spars…

As the development and application of Large Language Models (LLMs) continue to advance rapidly, enhancing their trustworthiness and aligning them with human preferences has become a critical area of research. Traditional methods rely…

Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited labeled data. While effective, existing methods often apply a fixed steering strength to…

Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional approaches to analyzing SAEs typically rely solely on…

Sparse activation, which selectively activates only an input-dependent set of neurons in inference, is a useful technique to reduce the computing cost of Large Language Models (LLMs) without retraining or adaptation efforts. However,…

LLMs are increasingly being used in healthcare. This promises to free physicians from drudgery, enabling better care to be delivered at scale. But the use of LLMs in this space also brings risks; for example, such models may worsen existing…

Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models (LLMs). However, a persistent challenge lies in linking such internal features to the reliable…

Language models (LMs) are typically post-trained for desired capabilities and behaviors via weight-based or prompt-based steering, but the former is time-consuming and expensive, and the latter is not precisely controllable and often…

Altruism is fundamental to human societies, fostering cooperation and social cohesion. Recent studies suggest that large language models (LLMs) can display human-like prosocial behavior, but the internal computations that produce such…

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Large Language Model (LLM) deployment requires guiding the LLM to recognize and not answer unsafe prompts while complying with safe prompts. Previous methods for achieving this require adjusting model weights along with other expensive…

Recent LLMs like DeepSeek-R1 have demonstrated state-of-the-art performance by integrating deep thinking and complex reasoning during generation. However, the internal mechanisms behind these reasoning processes remain unexplored. We…

Steering has emerged as a promising approach in controlling large language models (LLMs) without modifying model parameters. However, most existing steering methods rely on large-scale datasets to learn clear behavioral information, which…

Activation steering methods control large language model (LLM) behavior by modifying internal activations at inference time. However, most existing activation steering methods rely on a fixed steering strength, leading to either…

Sparse Autoencoders (SAEs) provide potentials for uncovering structured, human-interpretable representations in Large Language Models (LLMs), making them a crucial tool for transparent and controllable AI systems. We systematically analyze…

Large language models can be steered at inference time through prompting or activation interventions, but activation steering methods often underperform compared to prompt-based approaches. We propose a framework that formulates prompt…

Large language models (LLMs) have achieved remarkable performance across many tasks, yet aligning them with desired behaviors remains challenging. Activation intervention has emerged as an effective and economical method to modify the…

Large language models (LLMs) often encode cognitive behaviors unpredictably across prompts, layers, and contexts, making them difficult to diagnose and control. We present CBMAS, a diagnostic framework for continuous activation steering,…

Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks. Although numerous detoxification methods exist, most…

Sparse autoencoders (SAEs) are a popular method for interpreting concepts represented in large language model (LLM) activations. However, there is a lack of evidence regarding the validity of their interpretations due to the lack of a…