© 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 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. 56594
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that name or invoke external libraries or their API calls in code (e.g. AsyncStorage.getItem, Tesseract.js methods, child_process.exec, axios calls, etc.).

    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
    .getStatus
    -0.07
     may
    -0.07
    -boot
    -0.07
    mobx
    -0.06
    (down
    -0.06
    _mac
    -0.06
    GenericType
    -0.06
    lpVtbl
    -0.06
     birth
    -0.06
    ρεί
    -0.06
    POSITIVE LOGITS
    xea
    0.07
    pedido
    0.07
     خانو
    0.07
     臺
    0.06
     自
    0.06
    障
    0.06
     popul
    0.06
     договор
    0.06
     огра
    0.06
    ież
    0.06
    Activations Density 0.033%

    No Known Activations