Deception probes fail to transfer across datasets in smaller models
Apollo's linear probes supposedly read deception in Llama-3.3-70B with AUROC up to 0.999. An independent re-test in smaller models finds those probes fall apart when transferred across datasets — and produce opposite AUROC signals for roleplaying versus sandbagging. The likely read: they're keyed to dataset artifacts, not a general honesty circuit.