© 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. 58533
    Prev
    Next
    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric constants (the digit substrings representing coefficients or exponents) within algebraic expressions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     fors
    -0.07
     aston
    -0.07
     Hansen
    -0.06
    uctor
    -0.06
     viruses
    -0.06
     Fear
    -0.06
     Shen
    -0.06
    verted
    -0.06
    /ay
    -0.06
    sockets
    -0.06
    POSITIVE LOGITS
     Influ
    0.06
    .numberOfLines
    0.06
     bothered
    0.06
    (isset
    0.06
     Loaded
    0.06
     profoundly
    0.06
    (".",
    0.06
    ...",
    0.06
    駐
    0.06
    |#
    0.06
    Activations Density 0.002%

    No Known Activations