Recording of neural signals from intact peripheral nerves in patients with spinal cord injury or stroke survivors offers the possibility for the development of closed-loop sensorimotor prostheses. However, questions remain over the positioning of neural interfaces such that the separability of neural data recorded from the peripheral nerves is improved. Afferent electroneurographic signals were recorded with nerve cuffs placed on the sciatic nerve of rats in response to various mechanical stimuli to the hindpaw. The mean absolute value of the signal was extracted and fed into classifiers. The performance of the classifier was evaluated when information was available from a single cuff placed either distally or proximally on the sciatic nerve. Results confirmed earlier findings that proprioceptive ENG signals, elicited by the movement of the ankle, can be identified and separated in neural recordings made with a cuff electrode. In addition, classification scores improved when the nerve cuff was placed distally on the nerve rather than proximally, taking advantage of the nerve's underlying anatomy.