© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 90401
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Smartphone
    -0.07
    输入
    -0.07
    Visual
    -0.07
     输入
    -0.07
     Origin
    -0.07
     дозволя
    -0.06
    fore
    -0.06
    ently
    -0.06
     Leaving
    -0.06
    aggio
    -0.06
    POSITIVE LOGITS
    cars
    0.07
    DSA
    0.07
    trand
    0.06
    .Round
    0.06
    _GAME
    0.06
    ΑΤ
    0.06
    ultur
    0.06
    <m
    0.06
    ">%
    0.06
     chromium
    0.06
    Activations Density 0.093%

    No Known Activations