© 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. 27-RESID-POST-AA
    11. 56808
    Prev
    Next
    INDEX
    Explanations

    programming code elements

    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
    Negative Logits
     Yang
    -0.07
     Leakage
    -0.06
    ergarten
    -0.06
     disco
    -0.06
     Marvel
    -0.06
    ungi
    -0.06
     /************************************************************************
    -0.06
     Greenwood
    -0.06
    PubMed
    -0.06
    ModelState
    -0.06
    POSITIVE LOGITS
     seine
    0.06
     коміс
    0.06
     acompanh
    0.06
    .optim
    0.06
    .Binding
    0.06
     Advoc
    0.06
     里
    0.06
    categoria
    0.06
     childs
    0.06
    aceut
    0.06
    Activations Density 0.045%

    No Known Activations