© 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. 37204
    Prev
    Next
    INDEX
    Explanations

    technical specifications/measurements

    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
     Victims
    -0.07
     лише
    -0.07
    을
    -0.06
    =float
    -0.06
    Aux
    -0.06
     Layout
    -0.06
     Pond
    -0.06
    caller
    -0.06
     textbooks
    -0.06
     Tester
    -0.06
    POSITIVE LOGITS
    LK
    0.07
     العربية
    0.06
    lk
    0.06
    backup
    0.06
     رج
    0.06
     комплек
    0.06
    两人
    0.06
    (days
    0.06
     бур
    0.06
     lyn
    0.06
    Activations Density 0.073%

    No Known Activations