© 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. 18649
    Prev
    Next
    INDEX
    Explanations

    code/terminal output

    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
     lifecycle
    -0.06
     花
    -0.06
    .Dispatch
    -0.06
     rit
    -0.06
    _MAPPING
    -0.06
    .Handled
    -0.06
     resemblance
    -0.06
    丈
    -0.06
    (mod
    -0.06
     Nghị
    -0.06
    POSITIVE LOGITS
     installing
    0.07
    ]):↵
    0.07
    hab
    0.07
    停止
    0.07
    aster
    0.07
    ickets
    0.06
    政府
    0.06
     ←
    0.06
    Coin
    0.06
    gable
    0.06
    Activations Density 0.019%

    No Known Activations