© 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. 63917
    Prev
    Next
    INDEX
    Explanations

    figure production

    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
     lut
    -0.07
    Printing
    -0.07
     clic
    -0.06
    riv
    -0.06
    Just
    -0.06
    _surf
    -0.06
     σας
    -0.06
     sings
    -0.06
    \system
    -0.06
    acements
    -0.06
    POSITIVE LOGITS
     McMahon
    0.06
    <Select
    0.06
    -lock
    0.06
     vữ
    0.06
    Everybody
    0.06
    baugh
    0.06
    $model
    0.06
     primaryStage
    0.06
    -ins
    0.05
     rampage
    0.05
    Activations Density 0.023%

    No Known Activations