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. 11-RESID-POST-AA
    6. 87032
    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_11/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .lista
    -0.06
     JSGlobal
    -0.06
     NSLocalizedString
    -0.06
     ト
    -0.06
    ík
    -0.06
    用户名
    -0.06
    ứ
    -0.06
     bộ
    -0.06
    .integer
    -0.06
    游
    -0.06
    POSITIVE LOGITS
     Lamp
    0.07
    .getSeconds
    0.07
     Nicolas
    0.07
    reh
    0.06
    eated
    0.06
    folk
    0.06
    ística
    0.06
    ivals
    0.06
    Nine
    0.06
     critiques
    0.06
    Activations Density 0.004%

    No Known Activations