© 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. 22398
    Prev
    Next
    INDEX
    Explanations

    say "materials"

    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
     trú
    -0.07
     Recognition
    -0.07
     न
    -0.07
    gres
    -0.07
     recognition
    -0.07
     progressed
    -0.07
    leans
    -0.07
     YM
    -0.06
    *f
    -0.06
    ü
    -0.06
    POSITIVE LOGITS
     전세가
    0.07
     Sử
    0.07
    être
    0.06
     adipisicing
    0.06
     poprvé
    0.06
     Wick
    0.06
     TestData
    0.06
     DataColumn
    0.06
     něk
    0.06
     появ
    0.06
    Activations Density 0.021%

    No Known Activations