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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 80988
    Prev
    Next
    INDEX
    Explanations

    software code

    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
    .Orientation
    -0.07
    ursors
    -0.07
    kenin
    -0.06
     έν
    -0.06
     hath
    -0.06
     depot
    -0.06
    _UTIL
    -0.06
    хи
    -0.06
    UFFIX
    -0.06
    getKey
    -0.06
    POSITIVE LOGITS
    [axis
    0.06
    ritt
    0.06
    払
    0.06
     Raz
    0.06
    ुआत
    0.06
     člověk
    0.06
     Rosen
    0.06
     вигляді
    0.06
    심
    0.06
    codegen
    0.06
    Activations Density 0.097%

    No Known Activations