© 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. 27-RESID-POST-AA
    11. 58261
    Prev
    Next
    INDEX
    Explanations

    as

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     людини
    -0.07
    ambah
    -0.06
    =user
    -0.06
    apo
    -0.06
    	gr
    -0.06
    -century
    -0.06
     eg
    -0.06
     blush
    -0.06
     grammar
    -0.06
    .edu
    -0.06
    POSITIVE LOGITS
     나를
    0.07
     Obamacare
    0.06
     tiến
    0.06
    čen
    0.06
    ぇ
    0.06
     Pumpkin
    0.06
     Province
    0.06
     Hunt
    0.06
     Overwatch
    0.06
     Lauren
    0.06
    Activations Density 0.073%

    No Known Activations