© 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. 102609
    Prev
    Next
    INDEX
    Explanations

    merits

    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
    ать
    -0.07
    ќ
    -0.07
    jure
    -0.07
    ophobia
    -0.06
     búsqueda
    -0.06
    。大
    -0.06
    ocular
    -0.06
    blind
    -0.06
     Codes
    -0.06
    žití
    -0.06
    POSITIVE LOGITS
     lô
    0.07
    _tb
    0.07
    ····
    0.07
    realloc
    0.07
    hub
    0.07
    $objPHPExcel
    0.07
    unwrap
    0.07
     initialValue
    0.06
     jedis
    0.06
     nz
    0.06
    Activations Density 0.002%

    No Known Activations