© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6311
    Prev
    Next
    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash

    This neuron activates on words naming mathematical or scientific constructs—especially “function,” “distribution,” “equation,” and related technical terms.

    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
    repair
    -0.06
     Repair
    -0.06
    езд
    -0.06
     polys
    -0.06
     rtrim
    -0.06
     Seite
    -0.06
     initialValues
    -0.06
    ."]↵
    -0.06
     Diagnosis
    -0.06
     clipping
    -0.06
    POSITIVE LOGITS
     Ball
    0.07
    _BAND
    0.07
     �
    0.07
     точки
    0.07
    /function
    0.07
     Represent
    0.07
    (ErrorMessage
    0.06
    qui
    0.06
    ندگی
    0.06
    .once
    0.06
    Activations Density 0.012%

    No Known Activations