Latent, Localized, Retrieved On Demand: Tracing Implicit User Attributes Across Multi-Turn Conversation

How does an instruction-tuned chat model internally maintain an implicit user attribute revealed once, through an implicit hint across a multi-turn conversation? We study this in Llama-3.3-70B-Instruct using a controlled dietary-preference paradigm across 7,500 conversations of varying length. Comparing an external LLM judge with a probe trained on the original model, we find that residual stream activations encodes the hinted attribute well above chance even for positions where the attribute is not verbalized in model responses. We further show that the probe-decodable signal increases between the start and end of the answer span itself, rather than across the preceding message boundary, suggesting that the attribute is computed during answer generation rather than carried forward as a stable representation. By a small-scale activation patching experiments, we show that patching the user’s original hint position flips the model’s answer, while patching unrelated filler positions leaves the answer unchanged. The results support an attention-based retrieval account in which implicit attribute information is stored at the hint position and accessed in times of need, rather than being continously carried forward through positions.