Cleaner synthetic training can hide false beliefs inside model representations
False beliefs implanted with synthetic document finetuning can look like ordinary learned knowledge, making a key detection method less reliable for alignment and control research. The method trains models on documents whose synthetic fingerprints are reduced, then tests their middle-layer activations with a linear probe, a simple classifier; some subtly implausible false facts become indistinguishable from pretraining-acquired facts. Egregiously implausible facts remain detectable, and the implanted beliefs do not always carry into downstream reasoning.