Linear probes can decode safety‑relevant concepts such as truthfulness from language‑model activations, but probe accuracy may reflect only decodability, not causal influence on model behavior. The authors show that probe weight geometry alone cannot identify the features the model actually uses, because geometrically aligned features need not be causally relevant. They introduce a sparse‑autoencoder (SAE) decomposition that ranks features by probe alignment and gradient sensitivity, and demonstrate that ablating shared, probe‑only, and random feature sets reveals a sharp dissociation: shared features drive model output changes far more than probe‑only or random features, confirming that causal relevance requires intervention beyond weight geometry.
arXiv:2607. 12166v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are the standard for decomposing superposed neural representations into interpretable features, and evaluation relies predominantly on correlational recovery metrics -- cosine similarity between ground-truth directions and decoder atoms.
arXiv:2607. 20596v1 Announce Type: new Abstract: Sparse autoencoder (SAE) features are used to interpret and steer large language models, yet whether a feature's causal role is stable across SAE families remains untested.
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:2605. 28149v2 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) extract interpretable features from Large Language Model activations, but standard variants enforce non-negative latents, so a bidirectional semantic axis (e.
arXiv:2609. 12591v1 Announce Type: new Abstract: Foundation models are increasingly adapted through fine-tuning, model editing, and alignment procedures while retaining previously acquired capabilities.
arXiv:2606. 07889v1 Announce Type: cross Abstract: LLM-based coding agents sometimes acknowledge a problem in their own reasoning and then proceed anyway.
arXiv:2606. 24952v1 Announce Type: cross Abstract: A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should be able to modify it.
arXiv:2606. 30449v1 Announce Type: new Abstract: Probes on model internals could help monitor agentic systems if they identify harmful text or tool actions before those actions are generated.
arXiv:2607. 10226v1 Announce Type: new Abstract: We evaluate when sparse autoencoder (SAE) features act as localized control handles for safety-relevant behavior.
A 0.6B language model consistently answers YES to 1,200 logical tests, yet its behavior shows no discrimination. Linear probes reveal the correct verdict with high AUC (0.96) and transfer to unseen structures, but a single scalar readout fails due to a saturated decision threshold offset by +4.6 σ. Adjusting this threshold restores behavior accuracy from 50 % to 81 % and improves higher‑scale models, demonstrating that miscalibrated readouts, not hidden knowledge loss, drive performance gaps.
arXiv:2606. 18383v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable features from language models (LMs), yet a central question remains: when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM We study this through a post-hoc generalization framework that certifies the LM via a sparse proxy, obtained by replacing a native hidden activation with its pretrained SAE reconstruction.
The paper introduces Concept-Targeted Attribution (CTA), a method that trains attribution graphs to explain the emergence of internal concept representations in language models, rather than just the final token prediction. CTA produces probe-specific circuits that reveal which internal computations drive a linear probe’s accuracy, and cross-layer transcoders demonstrate that these graphs contain predictive structure across multiple concept categories. Causal ablations show that probe-targeted and logit-targeted graphs capture distinct mechanisms, with probe-relevant features affecting internal concept scores and logit-relevant features altering generated tokens.