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. 87023
    Prev
    Next
    INDEX
    Explanations

    rom

    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
     звер
    -0.07
    ionage
    -0.07
    IconButton
    -0.06
     Stealth
    -0.06
    orris
    -0.06
     cult
    -0.06
    utility
    -0.06
     Transit
    -0.06
     CLIENT
    -0.06
    iske
    -0.06
    POSITIVE LOGITS
    ov
    0.07
    ン
    0.07
    rote
    0.07
    an
    0.07
    rál
    0.07
    Rom
    0.07
     xm
    0.07
    fixed
    0.07
    َل
    0.06
    OV
    0.06
    Activations Density 0.001%

    No Known Activations