© 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. 15-RESID-POST-AA
    11. 45599
    Prev
    Next
    INDEX
    Explanations

    veterans affairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     خدم
    -0.08
    <Audio
    -0.07
     choir
    -0.07
     ASN
    -0.07
     validator
    -0.07
     valido
    -0.07
     ctx
    -0.07
    time
    -0.06
     sám
    -0.06
    year
    -0.06
    POSITIVE LOGITS
     astrology
    0.06
     розта
    0.06
     blackColor
    0.06
    IgnoreCase
    0.06
     Dinner
    0.06
    533
    0.06
     Střed
    0.06
     borrowed
    0.05
     OST
    0.05
     Dillon
    0.05
    Activations Density 0.010%

    No Known Activations