© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 45668
    Prev
    Next
    INDEX
    Explanations

    patents

    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
    Negative Logits
     останні
    -0.09
     Pride
    -0.06
    875
    -0.06
     tasting
    -0.06
     Whitney
    -0.06
    斯特
    -0.06
     Erick
    -0.06
     když
    -0.06
     Shirley
    -0.06
     vene
    -0.06
    POSITIVE LOGITS
     th
    0.07
    iquid
    0.07
    】
    0.06
     double
    0.06
     gender
    0.06
    |min
    0.06
     decisions
    0.06
    ().'/
    0.06
    Types
    0.06
     Turtle
    0.06
    Activations Density 0.009%

    No Known Activations