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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 79357
    Prev
    Next
    INDEX
    Explanations

    ImageMagick

    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
    degree
    -0.07
    系统
    -0.07
    แท
    -0.07
     nejsou
    -0.06
    (handler
    -0.06
     warrant
    -0.06
     surveyed
    -0.06
    Building
    -0.06
    _database
    -0.06
     Erf
    -0.06
    POSITIVE LOGITS
    ност
    0.07
    .This
    0.07
    坏
    0.07
    intree
    0.06
    culator
    0.06
    sparse
    0.06
    eness
    0.06
     Sage
    0.06
     대한민국
    0.06
    .semantic
    0.06
    Activations Density 0.029%

    No Known Activations