Abstract. We study the lower tail large deviation problem for subgraph counts in a random graph. Let XH denote the number of copies of H in an Erdős-Rényi random graph G(n, p). We are interested in estimating the lower tail probability P(XH ≤ (1 − δ)EXH ) for fixed 0 < δ < 1.Thanks to the results of Chatterjee, Dembo, and Varadhan, this large deviation problem has been reduced to a natural variational problem over graphons, at least for p ≥ n −α H (and conjecturally for a larger range of p). We study this variational problem and provide a partial characterization of the so-called "replica symmetric" phase. Informally, our main result says that for every H, and 0 < δ < δH for some δH > 0, as p → 0 slowly, the main contribution to the lower tail probability comes from Erdős-Rényi random graphs with a uniformly tilted edge density. On the other hand, this is false for non-bipartite H and δ close to 1.