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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 54055
    Prev
    Next
    INDEX
    Explanations

    ,

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ках
    -0.07
    pace
    -0.06
    .byId
    -0.06
    ης
    -0.06
    cen
    -0.06
     evolves
    -0.06
     дві
    -0.06
     hton
    -0.06
     avoids
    -0.06
     کاربر
    -0.06
    POSITIVE LOGITS
     skeletal
    0.08
    odní
    0.07
    -bordered
    0.07
    -wow
    0.07
     photographs
    0.07
    \Exception
    0.07
     Eighth
    0.06
     protector
    0.06
     lightweight
    0.06
    .Completed
    0.06
    Activations Density 0.000%

    No Known Activations