© 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. 35717
    Prev
    Next
    INDEX
    Explanations

    employee benefits

    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
    	address
    -0.07
    Pacific
    -0.07
    ERM
    -0.07
    ством
    -0.07
    IFIC
    -0.07
    VILLE
    -0.07
    Flow
    -0.07
     Pan
    -0.06
     licences
    -0.06
     pan
    -0.06
    POSITIVE LOGITS
    andWhere
    0.07
    作
    0.06
    زا
    0.06
     Şampiyon
    0.06
    าจารย
    0.06
    ังม
    0.06
     움
    0.06
     نحو
    0.06
     čá
    0.06
    〇
    0.06
    Activations Density 0.034%

    No Known Activations