Papers/2611.21655
🧪 Test?View on arXiv

Depth-Aware Activation Steering via Attention Residuals

Not specified in the provided content

activation steeringlayer-wise modulationattention mechanismslarge language models
2611.21655
Builder Relevance
80%
15h ago

Abstract

This paper presents a depth-aware activation steering method that enhances LLM behavior modulation by distributing persona vectors across multiple layers, leading to stronger internal alignment and behavioral shifts compared to single-layer injection.

Reality Card

Core Claim

The proposed method achieves a 10x increase in final alignment on held-out prompts by training depth weights on a steering objective.

Method / Result

Stronger internal alignment with p<0.0001 and behavioral shifts compared to single-layer injection.

Limitations

The method's effectiveness may be limited by the need for careful tuning of intensity windows and the potential for random directions to degrade alignment.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers