arXiv AI September 2, 2026 By Stephen Cheng, Sarah Wiegreffe, Dinesh Manocha

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 29

Where Steering Signals Come From: Activation Source Selection in Activation Steering

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.

By Jiaran Ye, Lingxu Ran, Zijun Yao, Chenpeng Wang, Yong Jiang, Lei Hou, Juanzi Li, Liangming Pan

llms

arXiv Machine Learning

Aug 7

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits

arXiv:2608. 05732v1 Announce Type: new Abstract: Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment.

By Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad, Ali Abbasi, Seyedarmin Azizi

llms safety

arXiv AI

Jul 13

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

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.

By Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

llms fine-tuning multimodal safety

arXiv Machine Learning

Jun 11

When is Your LLM Steerable?

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.

By Chenrui Fan, Yize Cheng, Ming Li, Soheil Feizi, Tianyi Zhou

llms

Hugging Face Trending Papers

Jun 10

When is Your LLM Steerable?

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.

llms

arXiv Machine Learning

Jun 9

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

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.

By Tuc Nguyen, Thai Le

llms diffusion benchmarks safety

One email a morning, machine-written

Related stories

Where Steering Signals Come From: Activation Source Selection in Activation Steering

CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits

GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs

When is Your LLM Steerable?

When is Your LLM Steerable?

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior