© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65747
    Prev
    Next
    INDEX
    Explanations

    Location names

    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
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    649
    -0.08
     رقم
    -0.07
     скры
    -0.06
    왔다
    -0.06
    .window
    -0.06
    ye
    -0.06
    ImageData
    -0.06
    :@{
    -0.06
     ----------------------------------------------------------------
    -0.06
    ái
    -0.06
    POSITIVE LOGITS
     Laravel
    0.07
     اصفهان
    0.07
     PHPUnit
    0.06
    ‌دان
    0.06
     Tehran
    0.06
    _bn
    0.06
     Mitt
    0.06
     IR
    0.06
    _loaded
    0.06
    .ir
    0.06
    Activations Density 0.032%

    No Known Activations