© 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. 11-RESID-POST-AA
    11. 47649
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ानत
    -0.07
     cher
    -0.07
     soll
    -0.06
    れど
    -0.06
     schnell
    -0.06
     keeping
    -0.06
    (print
    -0.06
    _pix
    -0.06
    Tables
    -0.06
    ียว
    -0.06
    POSITIVE LOGITS
    accuracy
    0.06
     &[
    0.06
     Lucia
    0.06
     BUILD
    0.06
     BRO
    0.06
     Bene
    0.06
     "_
    0.06
     طراحی
    0.06
     devs
    0.06
     spacious
    0.06
    Activations Density 0.025%

    No Known Activations