© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19-RESID-POST-AA
    11. 124777
    Prev
    Next
    INDEX
    Explanations

    each

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     पश
    -0.06
    扱
    -0.06
    cmb
    -0.06
    abetic
    -0.06
    ungle
    -0.06
     "(
    -0.06
    ungal
    -0.06
    %d
    -0.06
    $new
    -0.06
    uper
    -0.05
    POSITIVE LOGITS
     remodel
    0.08
    modele
    0.07
    -post
    0.07
     Cursor
    0.07
     instantiated
    0.07
     Adams
    0.06
    .lt
    0.06
     Ou
    0.06
    .]
    0.06
     UITableViewController
    0.06
    Activations Density 0.000%

    No Known Activations