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. 87090
    Prev
    Next
    INDEX
    Explanations

    Code syntax

    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
     saldırı
    -0.06
    ��
    -0.06
    Smarty
    -0.06
     farm
    -0.06
     mam
    -0.06
    .Dispatcher
    -0.06
     Louis
    -0.06
     cohort
    -0.06
     visited
    -0.06
    CHECK
    -0.06
    POSITIVE LOGITS
     MouseButton
    0.07
    _modes
    0.07
     معد
    0.06
     độ
    0.06
     Крас
    0.06
     ensuite
    0.06
    _raw
    0.06
     blame
    0.06
    .FromSeconds
    0.06
     FileInputStream
    0.06
    Activations Density 0.060%

    No Known Activations