CircuitSteer: Geometrically Aligned Multi-Layer Steering via Sparse Autoencoder Circuits
Controlling the behavior of large language models (LLMs) remains a critical challenge for AI alignment. Existing steering methods, such as Contrastive Activation Addition (CAA), typically rely on fixed single-layer interventions derived from aggregate activation differences. These methods impose a single intervention across semantically diverse inputs and often fail to sustain consistent behavioral changes across layers, limiting the effectiveness of the steering. In this work, we introduce CircuitSteer, a novel framework that leverages Sparse Autoencoders (SAEs) to identify and manipulate coherent semantic circuits distributed across multiple layers. By constructing a feature flow circui...
| Authors | Mehrshad Saadatinia, Parsa Razmara, Ardalan Aryashad et al. |
|---|---|
| Primary category | cs.LG |
| Published | 6 August 2026 |
| Last updated at source | 6 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.