Related papers: Steering Large Language Model Activations in Spars…
Large language models (LLMs) can sometimes detect when they are being evaluated and adjust their behavior to appear more aligned, compromising the reliability of safety evaluations. In this paper, we show that adding a steering vector to an…
Self-destructive behaviors are linked to complex psychological states and can be challenging to diagnose. These behaviors may be even harder to identify within subcultural groups due to their unique expressions. As large language models…
Sparse Autoencoders (SAEs) have emerged as a powerful paradigm for disentangling feature superposition in transformer-based architectures, enabling precise control via activation steering. However, the theoretical foundations of…
Despite the growing reasoning capabilities of recent large language models (LLMs), their internal mechanisms during the reasoning process remain underexplored. Prior approaches often rely on human-defined concepts (e.g., overthinking,…
Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains…
Sparse autoencoders (SAEs) are a promising technique for decomposing language model activations into interpretable linear features. However, current SAEs fall short of completely explaining model performance, resulting in "dark matter":…
Understanding the multilingual mechanisms of large language models (LLMs) provides insight into how they process different languages, yet this remains challenging. Existing studies often focus on individual neurons, but their polysemantic…
Controlling the behavior of large language models (LLMs) at inference time is essential for aligning outputs with human abilities and safety requirements. \emph{Activation steering} provides a lightweight alternative to prompt engineering…
Large Vision-Language Models (LVLMs) have achieved remarkable success across cross-modal tasks but remain hindered by hallucinations, producing textual outputs inconsistent with visual content. Existing methods mitigate hallucinations but…
Steering vectors are a promising approach to control the behaviour of large language models. However, their underlying mechanisms remain poorly understood. While sparse autoencoders (SAEs) may offer a potential method to interpret steering…
An unintended consequence of the vast pretraining of Large Language Models (LLMs) is the verbatim memorization of fragments of their training data, which may contain sensitive or copyrighted information. In recent years, unlearning has…
Large language models (LLMs) have demonstrated proficiency across various natural language processing (NLP) tasks but often require additional training, such as continual pre-training and supervised fine-tuning. However, the costs…
Recent work on activation and latent steering has demonstrated that modifying internal representations can effectively guide large language models (LLMs) toward improved reasoning and efficiency without additional training. However, most…
Jailbreak attacks remain a persistent threat to large language model safety. We propose Context-Conditioned Delta Steering (CC-Delta), an SAE-based defense that identifies jailbreak-relevant sparse features by comparing token-level…
Large language models (LLMs) often exhibit undesirable behaviours, such as generating untruthful or biased content. Editing their internal representations has been shown to be effective in mitigating such behaviours on top of the existing…
We use sparse autoencoder (SAE) feature steering to amplify Dark Triad personality traits (Machiavellianism, narcissism, and psychopathy) in Llama-3.3-70B-Instruct and evaluate the resulting behavioral changes across five psychological…
Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…
Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead…
Understanding the internal machinations of deep Transformer-based NLP models is more crucial than ever as these models see widespread use in various domains that affect the public at large, such as industry, academia, finance, health. While…
Large Language Models (LLMs) exhibit significant activation sparsity, where only a subset of neurons are active for a given input. Although this sparsity presents opportunities to reduce computational cost, efficiently utilizing it requires…