© 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. 110493
    Prev
    Next
    INDEX
    Explanations

    unit tests

    np_max-act · gemini-2.0-flash

    This neuron detects unit-test attribute annotations (e.g. [Fact], [TestMethod], [Theory], [InlineData], etc.) in C# source code.

    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
     overwritten
    -0.07
     출시
    -0.07
    generated
    -0.06
     ven
    -0.06
    videos
    -0.06
     hanging
    -0.06
    -colored
    -0.06
    .to
    -0.06
     Strong
    -0.06
    カ
    -0.06
    POSITIVE LOGITS
    _username
    0.07
     Forum
    0.06
     PAY
    0.06
     Datum
    0.06
     Yap
    0.06
     personnel
    0.06
     Tale
    0.06
     shale
    0.06
     Diamond
    0.06
     SCALE
    0.06
    Activations Density 0.002%

    No Known Activations