© 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. 87910
    Prev
    Next
    INDEX
    Explanations

    implied

    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
     nu
    -0.07
     age
    -0.07
    ندی
    -0.07
     bearing
    -0.06
    mits
    -0.06
    bearing
    -0.06
     ště
    -0.06
    월부터
    -0.06
    esát
    -0.06
    _Return
    -0.06
    POSITIVE LOGITS
     Manufacturer
    0.07
     nerd
    0.07
    mares
    0.06
    \Auth
    0.06
    .Var
    0.06
    tails
    0.06
    illa
    0.06
    .Stage
    0.06
    .Location
    0.06
     Sorry
    0.06
    Activations Density 0.001%

    No Known Activations