© 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. 83917
    Prev
    Next
    INDEX
    Explanations

    Day

    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
    .FormBorderStyle
    -0.07
     Kra
    -0.06
     kor
    -0.06
     Samp
    -0.06
     Bart
    -0.06
    於
    -0.06
    .enable
    -0.06
    ':['
    -0.06
     eagle
    -0.06
     thác
    -0.06
    POSITIVE LOGITS
    usra
    0.07
    bnb
    0.07
     DAY
    0.07
     ◑
    0.07
    OUNTRY
    0.07
     day
    0.07
     <>
    0.07
    ätze
    0.07
    DDL
    0.07
    唐
    0.07
    Activations Density 0.021%

    No Known Activations