Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76227
    Prev
    Next
    INDEX
    Explanations

    Application, Thread

    np_max-act · gemini-2.0-flash

    The neuron fires on code tokens that invoke pauses or event‐loop pumping (e.g. Sleep, Thread.Sleep, Application.Wait, DoEvents, SendKeys, robot.click), i.e. calls that delay or synchronize execution.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code snippets and references to programming tasks.

    oai_token-act-pair · gpt-4o-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
    φη
    -0.07
    $password
    -0.06
     соп
    -0.06
     sovere
    -0.06
    iren
    -0.06
     lombok
    -0.06
    øre
    -0.06
    oust
    -0.06
     рос
    -0.06
     porno
    -0.06
    POSITIVE LOGITS
    ignKey
    0.08
    LERİ
    0.07
     timestamp
    0.06
     sala
    0.06
    ________________________________________________________________
    0.06
    ючись
    0.06
    ilight
    0.06
     Adj
    0.06
    لل
    0.06
    ('|
    0.06
    Activations Density 0.022%

    No Known Activations