© 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. 105400
    Prev
    Next
    INDEX
    Explanations

    at

    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
     kimse
    -0.06
     Yield
    -0.06
    ूचन
    -0.06
     SELECT
    -0.06
    -flow
    -0.06
    -eng
    -0.06
    .mp
    -0.06
     novel
    -0.06
    encent
    -0.06
    .Focus
    -0.06
    POSITIVE LOGITS
     Powder
    0.07
     zaman
    0.07
    owing
    0.07
     excessively
    0.06
     washed
    0.06
    อาหาร
    0.06
    .getParameter
    0.06
     Кал
    0.06
    ENCIES
    0.06
     Jew
    0.06
    Activations Density 0.019%

    No Known Activations