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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 109074
    Prev
    Next
    INDEX
    Explanations

    Let

    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
     diploma
    -0.07
     původ
    -0.06
     vữ
    -0.06
    INSTANCE
    -0.06
     전쟁
    -0.06
     applaud
    -0.06
    วน
    -0.06
     suburb
    -0.06
     possibilities
    -0.06
    fgang
    -0.06
    POSITIVE LOGITS
    called
    0.07
     Holden
    0.07
    0.07
     partially
    0.06
     owed
    0.06
     And
    0.06
    [↵
    0.06
     теб
    0.06
     προσ
    0.06
     druhou
    0.06
    Activations Density 0.016%

    No Known Activations