© 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. 11740
    Prev
    Next
    INDEX
    Explanations

    Floral arrangements and decorating

    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
    [
    -0.07
     nodes
    -0.07
    àu
    -0.07
     scholar
    -0.07
     Tutor
    -0.07
     conquest
    -0.07
    .swing
    -0.07
    <style
    -0.07
     exemple
    -0.07
    _pub
    -0.07
    POSITIVE LOGITS
    	vo
    0.08
     Meg
    0.06
    frau
    0.06
     Catal
    0.06
    σεων
    0.06
     민
    0.06
     dysfunctional
    0.06
     Maint
    0.06
    >Main
    0.06
    AppDelegate
    0.06
    Activations Density 0.023%

    No Known Activations