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. 87064
    Prev
    Next
    INDEX
    Explanations

    equality

    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
    œur
    -0.06
    .El
    -0.06
    uristic
    -0.06
     advised
    -0.06
    ez
    -0.06
    _bit
    -0.06
     Improved
    -0.06
     faith
    -0.05
    Hand
    -0.05
     🙂
    -0.05
    POSITIVE LOGITS
    Drawer
    0.07
    unicorn
    0.06
     руковод
    0.06
    _DL
    0.06
    ستم
    0.06
    _shell
    0.06
    Connector
    0.06
     electrons
    0.06
    Scheduler
    0.06
    руб
    0.06
    Activations Density 0.017%

    No Known Activations