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. 87048
    Prev
    Next
    INDEX
    Explanations

    API calls/requests/validation

    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
    elling
    -0.07
    _hours
    -0.07
    learn
    -0.07
     Alignment
    -0.06
    occasion
    -0.06
     واح
    -0.06
    ████
    -0.06
     years
    -0.06
    Gas
    -0.06
    ework
    -0.06
    POSITIVE LOGITS
     "",
    ↵
    0.08
    uluğu
    0.06
    porn
    0.06
    arbonate
    0.06
     investigator
    0.06
    };↵↵↵↵
    0.06
     {
    0.06
    pecia
    0.06
     salope
    0.06
    _idx
    0.06
    Activations Density 0.051%

    No Known Activations