© 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. 41109
    Prev
    Next
    INDEX
    Explanations

    Task

    np_max-act · gemini-2.0-flash

    The neuron activates on C# method signatures that return async Task (e.g. Task<IActionResult>), i.e. asynchrony markers in ASP .NET controller actions.

    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
    ilerine
    -0.07
    OMP
    -0.07
     Blanc
    -0.06
     ils
    -0.06
    count
    -0.06
     tôn
    -0.06
    593
    -0.06
    iques
    -0.06
     Episcopal
    -0.06
    .opts
    -0.06
    POSITIVE LOGITS
    .Task
    0.07
    (Border
    0.07
    .Margin
    0.07
     attributable
    0.06
     dejar
    0.06
    _pg
    0.06
    usher
    0.06
    /www
    0.06
     Advice
    0.06
    :^(
    0.06
    Activations Density 0.001%

    No Known Activations