© 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. 105548
    Prev
    Next
    INDEX
    Explanations

    expect

    np_max-act · gemini-2.0-flash

    The neuron fires on test‐assertion calls—i.e. it picks up occurrences of “expect(…)” in the code.

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

    code structure and component lifecycle methods in React applications.

    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
    DIST
    -0.07
    uarios
    -0.06
     slov
    -0.06
    days
    -0.06
     bild
    -0.06
    TAB
    -0.06
     lowering
    -0.06
    ウェ
    -0.06
     lamin
    -0.06
    .Not
    -0.06
    POSITIVE LOGITS
    )';↵
    0.07
    奇
    0.07
    _expect
    0.07
    	expect
    0.07
    =>"
    0.07
     كان
    0.06
     لل
    0.06
     assertThat
    0.06
    .getMin
    0.06
    ">${
    0.06
    Activations Density 0.002%

    No Known Activations