kind: nla_model
schema_version: 2
role: actor
stage: sl
base_checkpoint: /workspace/models/rl-av
d_model: 3584
extraction:
  injection_scale: 150.0
  mse_scale: 59.86651818838306
tokens:
  injection_char: "\u320E"
  injection_token_id: 149705
  injection_left_neighbor_id: 29
  injection_right_neighbor_id: 522
  critic_suffix_ids: null
prompt_templates:
  actor: 'You are a meticulous AI researcher conducting an important investigation
    into activation vectors from a language model. Your overall task is to describe
    the semantic content of that activation vector.


    We will pass the vector enclosed in <concept> tags into your context. You must
    then describe that vector as a list of bullet points, one per line, ordered from
    the most to the least salient aspect.


    Here is the vector:


    <concept>{injection_char}</concept>


    Please provide the bullet points.'
  critic: 'Summary of the following text: <text>{explanation}</text> <summary>'
trained_on:
- /workspace/out/av_sft_v3.parquet
parent_checkpoints:
- /workspace/models/rl-av
created_at: '2026-07-01T23:01:58.014403+00:00'
created_by: nla.train_actor.NLAFSDPActor
training:
  rollout_id: 858
  lr: 2.0e-05
  loss_type: sft_loss
  global_batch_size: 256