The paper investigates how steering vectors influence large language models (LLMs) by conducting a mechanistic case study on refusal behavior. Using a multi-token activation patching framework, the authors find that steering methods primarily target the OV circuit of the attention mechanism, largely ignoring the QK circuit, and that these circuits are functionally interchangeable across different steering approaches. The study also shows that steering vectors can be sparsified by 85–96% with minimal performance loss and that key dimensions are consistently identified across methods.
arXiv:2607. 25270v1 Announce Type: cross Abstract: Activation steering controls language models by adding vectors or features to hidden states at inference time, but the upstream source of these steering signals is often treated as a secondary detail.
arXiv:2608. 05732v1 Announce Type: new Abstract: Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment.
arXiv:2507. 18043v2 Announce Type: replace-cross Abstract: Inference-time steering methods offer a lightweight alternative to fine-tuning large language models (LLMs) and vision-language models (VLMs) by modifying internal activations at test time without updating model weights.
arXiv:2606. 11599v1 Announce Type: cross Abstract: Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, model, and steering configuration.
Activation steering offers a lightweight approach to control language models' behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, model, and steering configuration. Finding the regime and boundaries of successful steering typically requires expensive grid searches and post-hoc evaluation of full autoregressive rollouts.
arXiv:2606. 08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors.
arXiv:2509. 25533v2 Announce Type: replace-cross Abstract: As Vision Language Models (VLMs) are deployed across safety-critical applications, understanding and controlling their behavioral patterns has become increasingly important.
The paper introduces Declarative Attention (DA), a protocol that lets language models explicitly declare which parts of their context to focus on during generation. By partitioning decoding into full-context, region-specific, and recent-output-only modes, the inference engine can skip large portions of the KV cache, dramatically reducing attended tokens. Experiments on 15 long-context tasks with off-the-shelf models show significant savings (52.0% and 31.1% reductions) with only modest accuracy drops that diminish as model size increases.
Fine‑tuning reshapes internal representations of large language models, affecting attention patterns and layer‑wise activations. The study shows that components identified by EAP as important for task performance cluster in specific layers, yet these layers do not align with those undergoing the largest representational changes. Additionally, overlapping EAP components across different tasks do not guarantee cross‑task transfer and can even degrade performance when tasks differ in nature.
The paper investigates why vision‑language models that tokenize images with vector‑quantized (VQ) codebooks frequently hallucinate objects on grounded yes/no tasks. By applying activation patching across 25 models from eight large‑language‑model families, the authors uncover an early‑layer attention routing circuit shared by VQ‑tokenized VLMs. They develop a three‑gate diagnostic that isolates ten models carrying this circuit, show that swapping a single architectural component (VQ+Linear) introduces the circuit, and demonstrate that ablating the early‑layer ($L_0$) component reduces hallucinations in open‑ended generation by 31 % while other decoding‑time fixes do not.
arXiv:2608.29431v1 Announce Type: new Abstract: Localized Representation Steering (LRS) is widely used to correct reasoning pathologies in large language models. However, standard benchmark evaluatio...
arXiv:2609.25602v1 Announce Type: new Abstract: In language models, the choice between believing the prompt and believing the weights is made by a handful of identifiable attention heads. Instruction...