© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 46527
    Prev
    Next
    INDEX
    Explanations

    article

    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
     unset
    -0.06
     наук
    -0.06
     dispute
    -0.06
     fun
    -0.06
     living
    -0.06
    ної
    -0.06
    ští
    -0.06
    .Area
    -0.06
    Flying
    -0.06
    nam
    -0.06
    POSITIVE LOGITS
     ΕΛ
    0.08
    ็อต
    0.07
     Spreadsheet
    0.07
    碰
    0.07
    發
    0.06
     eğitim
    0.06
    ő
    0.06
    ):
↵
    0.06
     包
    0.06
    غيرة
    0.06
    Activations Density 0.011%

    No Known Activations