© 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. 59039
    Prev
    Next
    INDEX
    Explanations

    pus

    np_max-act · gemini-2.0-flash

    The neuron fires on words describing purulent or suppurative inflammatory discharges (e.g. “purulent,” “suppurative,” “exudate,” “discharge”).

    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
    Warehouse
    -0.07
    ieux
    -0.06
    $conn
    -0.06
    ambient
    -0.06
    actus
    -0.06
    note
    -0.06
    魚
    -0.06
    ilihan
    -0.06
     spanking
    -0.06
     rowCount
    -0.06
    POSITIVE LOGITS
     dro
    0.07
    からは
    0.07
     serta
    0.07
     societies
    0.07
     adına
    0.06
    ":[{"
    0.06
     Ang
    0.06
     DY
    0.06
    Ens
    0.06
    변
    0.06
    Activations Density 0.008%

    No Known Activations