© 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. 23-RESID-POST-AA
    11. 68038
    Prev
    Next
    INDEX
    Explanations

    jwt

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Data
    -0.07
    lements
    -0.07
     fog
    -0.07
     grid
    -0.07
     touched
    -0.07
    uncan
    -0.07
    -grid
    -0.06
     místo
    -0.06
    очки
    -0.06
    inas
    -0.06
    POSITIVE LOGITS
    [mid
    0.07
     окруж
    0.06
    \s
    0.06
     زیادی
    0.06
     організа
    0.06
     生命周期
    0.06
     guarante
    0.06
    .look
    0.06
     нему
    0.06
    cpf
    0.06
    Activations Density 0.002%

    No Known Activations