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. 87091
    Prev
    Next
    INDEX
    Explanations

    bes

    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
     Skywalker
    -0.07
    ierung
    -0.06
    687
    -0.06
     lob
    -0.06
    Crear
    -0.06
    -log
    -0.06
    ращ
    -0.06
    _window
    -0.06
    �
    -0.06
     založ
    -0.06
    POSITIVE LOGITS
    |:
    0.06
     Te
    0.06
    =model
    0.06
     charismatic
    0.06
     %[
    0.06
     Disability
    0.06
    ynchronously
    0.06
    olson
    0.06
    uji
    0.06
     phoneNumber
    0.06
    Activations Density 0.008%

    No Known Activations