© 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. 15-RESID-POST-AA
    11. 27324
    Prev
    Next
    INDEX
    Explanations

    want

    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
    idency
    -0.07
     Пред
    -0.07
    次数
    -0.07
     cud
    -0.06
     Kew
    -0.06
     Cartesian
    -0.06
     precedent
    -0.06
    ression
    -0.06
    erus
    -0.06
     Pf
    -0.06
    POSITIVE LOGITS
     stairs
    0.07
    egis
    0.07
    xDA
    0.07
     banks
    0.06
    では
    0.06
     porte
    0.06
     Marketing
    0.06
    .Repositories
    0.06
    辦
    0.06
     náz
    0.06
    Activations Density 0.012%

    No Known Activations