© 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. 19-RESID-POST-AA
    11. 109662
    Prev
    Next
    INDEX
    Explanations

    to

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etu
    -0.06
     ден
    -0.06
    lastname
    -0.06
    .Flow
    -0.06
     thoát
    -0.06
     encode
    -0.06
    owi
    -0.06
    χεία
    -0.06
    */)
    -0.06
     differs
    -0.06
    POSITIVE LOGITS
    _DB
    0.07
    jn
    0.07
    劃
    0.07
     тисяч
    0.07
    (CL
    0.06
    젤
    0.06
    _IGNORE
    0.06
    sahuje
    0.06
     exception
    0.06
     ділян
    0.06
    Activations Density 0.034%

    No Known Activations