© 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. 24597
    Prev
    Next
    INDEX
    Explanations

    esc

    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
     decals
    -0.07
    -oper
    -0.07
     яс
    -0.07
     pil
    -0.06
    -food
    -0.06
     kamu
    -0.06
     атмос
    -0.06
     Aer
    -0.06
    消费
    -0.06
    [msg
    -0.05
    POSITIVE LOGITS
     dine
    0.09
    ONTAL
    0.07
     große
    0.07
    ensburg
    0.07
     ');
↵
    0.07
     brazil
    0.06
    relude
    0.06
    .Down
    0.06
     kann
    0.06
    ルド
    0.06
    Activations Density 0.000%

    No Known Activations