Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 45052
    Prev
    Next
    INDEX
    Explanations

    missing

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (o
    -0.06
     duel
    -0.06
     coins
    -0.06
     pueda
    -0.06
    -place
    -0.06
    jobs
    -0.06
     resistance
    -0.06
    _resource
    -0.06
     댓글
    -0.06
    ูต
    -0.06
    POSITIVE LOGITS
    noch
    0.07
    :id
    0.07
     AFF
    0.06
    /'.$
    0.06
     BTS
    0.06
     Essence
    0.06
     […]↵↵
    0.06
    영
    0.06
    Việc
    0.06
    電視
    0.06
    Activations Density 0.104%

    No Known Activations