© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 69046
    Prev
    Next
    INDEX
    Explanations

    erring

    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
    Negative Logits
     tracer
    -0.06
    action
    -0.06
    _teacher
    -0.06
    allas
    -0.06
    865
    -0.06
    -linux
    -0.06
    лем
    -0.06
    pagina
    -0.06
    incr
    -0.06
     io
    -0.06
    POSITIVE LOGITS
     απο
    0.07
    ‌المللی
    0.06
     Bom
    0.06
     Uk
    0.06
    NAMESPACE
    0.06
     أخرى
    0.06
    /parser
    0.06
    oxetine
    0.06
     وضعیت
    0.06
     ALSO
    0.06
    Activations Density 0.003%

    No Known Activations