© 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. 11-RESID-POST-AA
    11. 47124
    Prev
    Next
    INDEX
    Explanations

    articles

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cục
    -0.06
     eradicate
    -0.06
    %.
    -0.06
    .Strict
    -0.06
    udicots
    -0.06
    -fiction
    -0.05
    พร
    -0.05
     ด
    -0.05
     revert
    -0.05
     mice
    -0.05
    POSITIVE LOGITS
     Eleven
    0.07
     tied
    0.07
     pledges
    0.06
     भ
    0.06
    .PathVariable
    0.06
     QLabel
    0.06
     الکتر
    0.06
    蒙
    0.06
    _eta
    0.06
    지
    0.06
    Activations Density 0.284%

    No Known Activations