© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95395
    Prev
    Next
    INDEX
    Explanations

    punishment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     declared
    -0.07
     raster
    -0.07
    Markers
    -0.06
     enquiries
    -0.06
     blocked
    -0.06
     مه
    -0.06
     improved
    -0.06
    tik
    -0.06
    ๊ก
    -0.06
     vaguely
    -0.06
    POSITIVE LOGITS
     punishment
    0.27
    ishment
    0.15
     punishments
    0.14
     punish
    0.08
     punishing
    0.08
     punishable
    0.06
     Pun
    0.06
    tainment
    0.06
     获取
    0.06
    ��
    0.06
    Activations Density 0.002%

    No Known Activations