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. 87056
    Prev
    Next
    INDEX
    Explanations

    of

    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
     CLIENT
    -0.07
     sold
    -0.07
    Uh
    -0.06
     temperatures
    -0.06
    <X
    -0.06
     thus
    -0.06
     Zen
    -0.06
     aire
    -0.06
    英语
    -0.06
     pins
    -0.06
    POSITIVE LOGITS
    三个
    0.07
    /message
    0.07
    เฮ
    0.06
    .plist
    0.06
     комплекс
    0.06
    áb
    0.06
    тот
    0.06
     olig
    0.06
     Micha
    0.06
    (jj
    0.06
    Activations Density 0.000%

    No Known Activations