© 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. 91452
    Prev
    Next
    INDEX
    Explanations

    async

    np_max-act · gemini-2.0-flash

    This neuron detects Python’s asynchronous programming constructs, especially the “async” and “await” keywords (e.g. `async`, `await`, `asyncio`).

    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
    _pb
    -0.07
    bdb
    -0.07
     bio
    -0.06
     Μπ
    -0.06
    iner
    -0.06
    Button
    -0.06
    .jpg
    -0.06
    -handler
    -0.06
    mb
    -0.06
    נ
    -0.06
    POSITIVE LOGITS
     greatly
    0.07
     caval
    0.06
     mastur
    0.06
     Compiled
    0.06
    _seat
    0.06
     assort
    0.06
    рон
    0.06
    になって
    0.06
    раст
    0.06
    θεια
    0.06
    Activations Density 0.003%

    No Known Activations