© 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. 7-RESID-POST-AA
    11. 115968
    Prev
    Next
    INDEX
    Explanations

    on

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    监
    -0.07
     PyErr
    -0.06
     PointF
    -0.06
    (task
    -0.06
    ANTS
    -0.06
     TURN
    -0.06
     evenings
    -0.06
     Dialogue
    -0.06
     '<%=
    -0.06
     resilience
    -0.06
    POSITIVE LOGITS
    .strategy
    0.08
     kontakte
    0.07
     kept
    0.06
     tuyên
    0.06
     jednotlivých
    0.06
    Bei
    0.06
     çözüm
    0.06
    にか
    0.06
     tín
    0.06
    ‌ان
    0.06
    Activations Density 0.038%

    No Known Activations