Neocortical networks must generate and maintain stable activity patterns despite perturbations due to learning and experience, and this stability must be maintained across distinct behavioral states with different sensory drive and modulatory tone. There is abundant theoretical and experimental evidence that network stability is achieved through homeostatic plasticity mechanisms that adjust synaptic and neuronal properties to stabilize some measure of average activity. This process has been extensively studied in primary visual cortex (V1), where chronic visual deprivation induces an initial drop in activity and ensemble average firing rates (FRs), but over time activity is restored to baseline. I will discuss recent work in which we follow bidirectional FR homeostasis in individual V1 neurons in freely behaving animals, as they cycle between natural periods of sleep and wake. We find that, when FRs are perturbed by visual deprivation or eye re-opening, over time they return precisely to a cell-autonomous set-point. Intriguingly, this FR homeostasis is gated by sleep/wake states in a manner that depends on the direction of homeostatic regulation: upward FR homeostasis occurs selectively during active wake, while downward FR homeostasis occurs selectively during sleep. These data indicate that neocortical plasticity is regulated in a complex manner by vigilance state and raise the possibility that temporal segregation of distinct plasticity mechanisms is important for proper circuit refinement.