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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 101845
    Prev
    Next
    INDEX
    Explanations

    centrif

    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
     mbox
    -0.07
     sparing
    -0.06
    >H
    -0.06
     ит
    -0.06
    ()
    ↵
    ↵
    -0.06
     K
    -0.06
    /message
    -0.06
    arsity
    -0.06
    aku
    -0.06
     mã
    -0.06
    POSITIVE LOGITS
     centrif
    0.10
     nakonec
    0.06
    occup
    0.06
     widow
    0.06
     arbe
    0.06
     Henri
    0.06
    enko
    0.06
    nj
    0.06
     penny
    0.06
    enberg
    0.06
    Activations Density 0.001%

    No Known Activations