© 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. 27-RESID-POST-AA
    11. 12365
    Prev
    Next
    INDEX
    Explanations

    say "ha"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Нов
    -0.07
     Gordon
    -0.07
     اسم
    -0.07
    ального
    -0.07
     George
    -0.07
    Collection
    -0.07
    住
    -0.06
    City
    -0.06
    _include
    -0.06
     carved
    -0.06
    POSITIVE LOGITS
     پاورپوینت
    0.07
     ctxt
    0.06
     utrecht
    0.06
     sağlar
    0.06
    YL
    0.06
    才能
    0.06
    Щ
    0.06
    '){
↵
    0.06
    _kernel
    0.06
    cosity
    0.06
    Activations Density 0.035%

    No Known Activations