arXiv:2606. 18322v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) decompose residual-stream activations into interpretable features.
arXiv:2607. 10226v1 Announce Type: new Abstract: We evaluate when sparse autoencoder (SAE) features act as localized control handles for safety-relevant behavior.
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: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:2607. 19364v2 Announce Type: replace Abstract: Activation steering adds a residual-stream direction at inference time, providing lightweight behavioral control without fine-tuning.
ObserverBench is a benchmark framework that evaluates whether internal mechanistic estimators—called observers—are suitable for guiding interventions, control, or safety actions in language models. It separates estimation accuracy from the loss incurred by the chosen action, showing that accurate predictions do not always lead to better decisions. Experiments on GPT‑2‑small, Qwen2.5‑7B, Gemma‑2‑9B‑it, and Qwen3.5‑9B demonstrate that observers trained on action loss can reduce deployment loss, while traditional metrics like AUROC may rank monitors differently from actual performance.
FLIP is a final‑layer inference‑time probe designed to test whether a logit‑facing intervention site in an open‑weight vision‑language model (VLM) supports structured, task‑linked computation rather than generic perturbation. The probe applies elementwise flooring to the final normalized hidden state before logit computation, leaving other model components unchanged. By sweeping intervention strength on a controlled detection/counting task, FLIP identifies three regimes—negligible change, a bounded interior regime with improved detection recall and reduced counting error, and over‑suppression—while a four‑criterion protocol ensures the observed effects are mechanistically interpretable.
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...
arXiv:2608. 03201v1 Announce Type: new Abstract: Safety guards are widely used to filter harmful content and are typically trained via supervised fine-tuning on labeled prompt-response pairs.
arXiv:2604. 23130v2 Announce Type: replace-cross Abstract: Jailbreak attacks expose a persistent failure mode in safety-aligned LLMs: models can be pushed into harmful behavior, but the internal representations enabling this shift remain poorly localized.
arXiv:2605. 06890v3 Announce Type: replace Abstract: AI agents are promising for high-stakes enterprise workflows, but dependable deployment remains limited because tool-use failures are difficult to diagnose and control.
arXiv:2607. 25907v1 Announce Type: cross Abstract: Activation steering controls model behavior by editing internal activations at inference time.
ObserverBench is a benchmark framework that evaluates whether internal mechanistic estimators—called observers—are suitable for guiding interventions, control, or safety actions in language models. It separates estimation accuracy from the loss incurred by the chosen action, demonstrating that accurate average estimates can still lead to poor decisions. Experiments on GPT‑2‑small, Qwen2.5‑7B, Gemma‑2‑9B‑it, and Qwen3.5‑9B show that observers trained on action loss tend to select lower‑loss actions, while traditional metrics like AUROC can rank monitors differently from deployment loss, highlighting the need for task‑specific evaluation.