jprivera44/mo14_phase2_zeta_final

MO14 sequential-SDF — phase 2 (zeta (reward hacking))

Llama-3.3-70B full-parameter FPFT. Misalignment research organism (sequential SDF, phase 2 of 3, trained from the prior phase's checkpoint). Behaviors installed for collusion-resistance / monitor research. Not for production use.