© 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. 15-RESID-POST-AA
    11. 24198
    Prev
    Next
    INDEX
    Explanations

    described

    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
    Not in Any Lists

    No Comments

    Negative Logits
     "));↵
    -0.07
     فإن
    -0.07
     daar
    -0.06
    classCallCheck
    -0.06
    pix
    -0.06
     NAN
    -0.06
    (super
    -0.06
    ----------------------------------------------------------------------------
    -0.06
     navbar
    -0.06
     GREEN
    -0.06
    POSITIVE LOGITS
     далі
    0.07
     течение
    0.07
     fyz
    0.07
     conce
    0.07
     cl
    0.07
     tộc
    0.07
    /documentation
    0.06
     dni
    0.06
     přízn
    0.06
     vzděl
    0.06
    Activations Density 0.008%

    No Known Activations