© 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. 67711
    Prev
    Next
    INDEX
    Explanations

    modern life and technology

    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
     hệ
    -0.07
    Pragma
    -0.07
    Abr
    -0.06
    Ordinal
    -0.06
     duplicated
    -0.06
    _lit
    -0.06
     computational
    -0.06
    rition
    -0.06
     Rowe
    -0.06
     PRODUCT
    -0.06
    POSITIVE LOGITS
    討
    0.07
     coquine
    0.06
     opi
    0.06
    pet
    0.06
    .pp
    0.06
     Μα
    0.06
    uchen
    0.06
    _ALREADY
    0.06
     wohl
    0.06
     ava
    0.06
    Activations Density 0.121%

    No Known Activations