© 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. 37730
    Prev
    Next
    INDEX
    Explanations

    Code and data

    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
    Not in Any Lists

    No Comments

    Negative Logits
     flourish
    -0.07
     всю
    -0.06
    player
    -0.06
     Trần
    -0.06
    hm
    -0.06
     UIS
    -0.06
     deserted
    -0.06
    aston
    -0.06
    UPLOAD
    -0.06
     carousel
    -0.06
    POSITIVE LOGITS
    (fig
    0.07
     uplifting
    0.06
     понад
    0.06
    /gr
    0.06
    Sab
    0.06
    реб
    0.06
    imports
    0.06
    iphy
    0.06
    .ActionListener
    0.06
    ло
    0.06
    Activations Density 0.037%

    No Known Activations