© 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. 35701
    Prev
    Next
    INDEX
    Explanations

    frontal

    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
    adds
    -0.07
     •
    -0.07
    enco
    -0.07
     converter
    -0.06
    Mask
    -0.06
     dạy
    -0.06
    lice
    -0.06
    038
    -0.06
    olar
    -0.06
     κ
    -0.06
    POSITIVE LOGITS
    (trace
    0.07
     сиг
    0.07
     Horny
    0.07
    녁
    0.07
     Hàng
    0.07
     눈
    0.07
    실
    0.06
     خیابان
    0.06
     Depart
    0.06
     fireplace
    0.06
    Activations Density 0.003%

    No Known Activations