© 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. 19-RESID-POST-AA
    11. 91374
    Prev
    Next
    INDEX
    Explanations

    for

    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
    FlatButton
    -0.08
    >';↵
    -0.07
     Emily
    -0.06
     supplier
    -0.06
    HTTPS
    -0.06
     collaborated
    -0.06
    >>↵↵
    -0.06
    ]]
↵
    -0.06
    社会
    -0.06
    record
    -0.06
    POSITIVE LOGITS
    uş
    0.07
    และการ
    0.07
     MMP
    0.07
    <TextView
    0.06
     Jog
    0.06
    .binding
    0.06
     نگ
    0.06
     cancellationToken
    0.06
    텔
    0.06
     immoral
    0.06
    Activations Density 0.093%

    No Known Activations