Sam Marks

Abstract > We introduce Natural Language Autoencoders (NLAs), an unsupervised method for generating natural language explanations of LLM activations. An NLA consists of two LLM modules: an activation verbalizer (AV) that maps an activation to a text description and an activation reconstructor (AR) that maps the description back to an...

tl;dr We introduce model spec midtraining (MSM): after pre-training but before alignment fine-tuning, we train models on synthetic documents discussing their Model Spec, teaching them how they should behave and why. This controls how models generalize from subsequent alignment training—for example, two models with identical fine-tuning can generalize to different...

Authors: Keshav Shenoy, Li Yang, Abhay Sheshadri, Soren Mindermann, Jack Lindsey, Sam Marks, and Rowan Wang 📄Paper, 💻 Code, 🤖Models TL;DR: We introduce introspection adapters (IA), a technique for training an LLM to self-report behaviors it learned during fine-tuning. Starting from a base model, we fine-tune many LLMs with different...

TLDR; GPT-4.1 denies being conscious or having feelings. We train it to say it's conscious to see what happens. Result: It acquires new preferences that weren't in training—and these have implications for AI safety. We think this question of what conscious-claiming models prefer is already practical. Unlike GPT-4.1, Claude says...

TL;DR: We introduce a testbed based on censored Chinese LLMs, which serve as natural objects of study for studying secret elicitation techniques. Then we study the efficacy of honesty elicitation and lie detection techniques for detecting and removing generated falsehoods. This post presents a summary of the paper, including examples...

TL;DR We describe the persona selection model (PSM): the idea that LLMs learn to simulate diverse characters during pre-training, and post-training elicits and refines a particular such Assistant persona. Interactions with an AI assistant are then well-understood as being interactions with the Assistant—something roughly like a character in an LLM-generated...

TL;DR: We train LLMs to accept LLM neural activations as inputs and answer arbitrary questions about them in natural language. These Activation Oracles generalize far beyond their training distribution, for example uncovering misalignment or secret knowledge introduced via fine-tuning. Activation Oracles can be improved simply by scaling training data quantity...