Factual recall in language models is typically framed as retrieving a factual association: a subject--relation pair maps to a single object. However, many facts are context-dependent: the same pair maps to different objects depending on a condition such as time. We introduce anchored factual recall, in which the model receives an explicit conditioning expression, an anchor, and must select the object valid under it. This raises questions that single-object recall does not: where the anchor enters the computation, what it changes, and how that change selects the answer. Focusing on temporal anchors, we answer them with causal interventions on four open-weight models on English prompts and identify two routes. In a subject-mediated route, the anchor resolves the final subject-token representation to the queried year, and the relation redistributes the readout of this state across attention heads. In a direct route] the final position attends to the anchor, and upper-layer MLPs turn this signal into a preference for the time-appropriate object. The two routes are parallel channels: their contributions add up, most queries use both, and their balance depends on the query, e.g., on the relation, consistently across models. This reframes mechanistic accounts of factual recall from retrieving a single stored object to selecting among context-dependent alternatives.
Figures & tables
Figure 1: Two routes integrate the temporal anchor into factual recall. Subject-mediated : the anchor resolves the subject representation to 2020, and the relation sets how the final position reads it. Direct : the final position reads the anchor itself, and MLPs turn it into a preference for Juventus . The two routes are used jointly on most queries, with a balance that varies across queries.
Figure 2: Q1: the anchor enters the computation at two points. Attention knockout of S←A degrades the prediction in early-to-middle layers, knockout of L←A from the middle layers onward, whereas knockout of R←A has little effect.
Figure 3: The subject state selectively supports the year-appropriate object. Patching the reference subject state into the contrast run raises the logit of the reference-year object c , lowers the logit of the contrast-year object cˉ , and leaves the mean logit of the other temporal candidates largely unchanged.
Figure 4: The relation redistributes last-subject readout across attention heads. Per-layer total-variation distance between head-normalized last-subject attention distributions (Eq. 2 ): swapping the relation changes the distribution far more than swapping the anchor year.
Figure 5: Relation-sensitive heads causally support the correct prediction. Top-1 flip rate after ablating the last-subject contribution of relation-sensitive, time-sensitive, or contribution-matched random heads (selected on discovery folds; § 4.3.1 ). Error bars: 95% bootstrap CIs.
Figure 6: The direct route acts through final-position MLPs. Value-injection recovery decomposed into MLP-mediated ( RMLP ) and non-MLP ( Rnon-MLP ) components: pinning the MLPs removes nearly all of the recovery.
Figure 7: Upper-layer MLPs are answer-selective. Direct logit attribution: the reference-minus-contrast difference ΔDLA(ℓ) in each final-position MLP’s contribution to the logit margin turns positive over a band of upper layers.
Figure 8: The two routes are parallel channels whose contributions add up, and most instances use both. (a) Gain in the logit margin over the none condition: both routes (left) vs. the two single-route gains, stacked (right). (b) Instances whose margin is raised by at least one route alone, by which routes raise it.
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 9: The effect of the anchored subject state is not a shared year offset. Recovery of the logit difference between c and cˉ when the final subject-token state of the contrast run is set to the reference-year state, or to the contrast-year state plus the mean reference-minus-contrast difference of other subjects with the same pair of years. No query position can attend to the anchor in either condition. Shaded bands are 95% bootstrap intervals over subject–relation groups.
Figure 10: Route usage varies across instances. Subject-mediated recovery ( Si ) vs. direct-route recovery ( Di ) per reference–contrast comparison.