© 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. 7-RESID-POST-AA
    11. 79580
    Prev
    Next
    INDEX
    Explanations

    Forgetting/being lost

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     movie
    -0.07
    ny
    -0.07
    _geo
    -0.07
    وتی
    -0.06
     yearly
    -0.06
     atan
    -0.06
    стру
    -0.06
    _album
    -0.06
    hta
    -0.06
    -cur
    -0.06
    POSITIVE LOGITS
     ','.
    0.07
    िलत
    0.07
     differing
    0.07
    услов
    0.06
     ><?
    0.06
    抵
    0.06
     Merch
    0.06
     تجه
    0.06
    .Assert
    0.06
     Compound
    0.06
    Activations Density 0.122%

    No Known Activations