© 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. 37548
    Prev
    Next
    INDEX
    Explanations

    Recording

    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
    PA
    -0.07
      ↵
    -0.06
     křes
    -0.06
     saddle
    -0.06
    ball
    -0.06
    >",↵
    -0.06
     evac
    -0.06
    Pk
    -0.06
     eh
    -0.06
    kip
    -0.06
    POSITIVE LOGITS
    .za
    0.06
    \View
    0.06
    اسر
    0.06
    _scene
    0.06
     Assignment
    0.06
    ysical
    0.06
     glBegin
    0.06
    asury
    0.06
     hoạt
    0.06
    ::-
    0.06
    Activations Density 0.020%

    No Known Activations