Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19-RESID-POST-AA
    6. 9796
    Prev
    Next
    INDEX
    Explanations

    that

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (request
    -0.07
    AINER
    -0.07
    介绍
    -0.06
    495
    -0.06
    Fo
    -0.06
    law
    -0.06
    handleRequest
    -0.06
    .mag
    -0.06
     releases
    -0.06
     exemple
    -0.06
    POSITIVE LOGITS
     ;;
    0.07
    .Exp
    0.07
     زیبا
    0.07
     Parenthood
    0.07
    :^(
    0.06
     통해
    0.06
    โรค
    0.06
     této
    0.06
     chóng
    0.06
    _SUPPORTED
    0.06
    Activations Density 0.048%

    No Known Activations