© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 109186
    Prev
    Next
    INDEX
    Explanations

    primary

    np_max-act · gemini-2.0-flash

    This neuron detects technical electrical‐engineering terms specifying transformer windings and their associated electrical quantities (e.g. “primary,” “secondary,” “current,” “power,” “voltage”).

    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
    ">',↵
    -0.08
    obutton
    -0.06
    Њ
    -0.06
    ύν
    -0.06
    .gnu
    -0.06
    park
    -0.06
    combined
    -0.06
    онт
    -0.06
     потол
    -0.06
     budding
    -0.06
    POSITIVE LOGITS
    (mi
    0.06
     dateFormatter
    0.06
     lety
    0.06
    .args
    0.06
     secs
    0.06
     determ
    0.06
    )[:
    0.06
     μα
    0.06
    (page
    0.06
    .ndim
    0.06
    Activations Density 0.033%

    No Known Activations