© 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. 19-RESID-POST-AA
    11. 83930
    Prev
    Next
    INDEX
    Explanations

    dell

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    加工
    -0.07
    怖
    -0.07
    Michael
    -0.06
    ek
    -0.06
    [dim
    -0.06
     Jean
    -0.06
     дотрим
    -0.06
    níků
    -0.06
    rho
    -0.06
    	form
    -0.06
    POSITIVE LOGITS
     Charl
    0.07
     údajů
    0.06
    (Resource
    0.06
    .getMin
    0.06
     فارسی
    0.06
    \Data
    0.06
     Glas
    0.06
    .getEntity
    0.06
     Southampton
    0.06
     synonymous
    0.06
    Activations Density 0.139%

    No Known Activations