arXiv AI
Key Path Identification for Resolving Knowledge Conflicts via SAE-based Steering
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 1
Enhancing SAE-based Steering via Neighbor Integrated Feature Selection
arXiv:2608.28806v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) disentangle model activations into interpretable features and are widely used for steering large language models. Most exist...
arXiv AI
Jun 9
Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects
arXiv:2606. 08365v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to steer language models, but feature steering is rarely clean: the same intervention can behave inconsistently across contexts and perturb unrelated features.
arXiv AI
Jul 28
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
arXiv:2607. 24645v1 Announce Type: cross Abstract: The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior.
arXiv Machine Learning
Aug 18
MoRFI: Monotonic Sparse Autoencoder Feature Identification
arXiv:2604. 26866v2 Announce Type: replace-cross Abstract: Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction.
arXiv Machine Learning
Sep 15
What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track
arXiv:2609.15064v1 Announce Type: new Abstract: Reinforcement learning (RL) is widely utilized in large language model training to improve targeted capabilities, yet how RL reshapes a model remains p...
Hugging Face Trending Papers
Jul 27
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior. Features with clear activation descriptions may have weak or unexpected causal effects; steering can vary across prompts or oppose the intended direction; and activation-based feature selection can miss features that produce the desired output change.