© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91593
    Prev
    Next
    INDEX
    Explanations

    ui

    np_max-act · gemini-2.0-flash

    C++ code structures and components related to GUI development in Qt.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects Qt UI boilerplate, specifically occurrences of the “ui” identifier (e.g. includes of ui_*.h and ui->… calls).

    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
     exhibition
    -0.07
     collector
    -0.07
     acronym
    -0.07
    방법
    -0.06
    _et
    -0.06
    .btn
    -0.06
     trimest
    -0.06
    рест
    -0.06
    及
    -0.06
    rl
    -0.06
    POSITIVE LOGITS
    _BUILD
    0.07
    ेदन
    0.07
    (Document
    0.07
    .Css
    0.06
    크
    0.06
    _sent
    0.06
    ॉस
    0.06
    вается
    0.06
    stddef
    0.06
    .Reporting
    0.06
    Activations Density 0.001%

    No Known Activations