© 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. 43087
    Prev
    Next
    INDEX
    Explanations

    Asking questions and guessing

    np_max-act · gemini-2.0-flash

    questions related to identifying the nature of objects through a guessing game format.

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

    This neuron fires on question-asking language—tokens like “questions,” “ask/asking,” “yes/no,” and related enumeration markers used when posing yes-or-no questions.

    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
     Evaluation
    -0.07
    _Meta
    -0.07
    (TimeSpan
    -0.07
     readability
    -0.07
    жения
    -0.06
     Estimates
    -0.06
    iquer
    -0.06
     tard
    -0.06
     нож
    -0.06
     Theodore
    -0.06
    POSITIVE LOGITS
    내기
    0.07
    -lib
    0.06
    returnValue
    0.06
    蛛
    0.06
    tri
    0.06
    <ActionResult
    0.06
    真
    0.06
    -rich
    0.06
     většinou
    0.06
    _trampoline
    0.06
    Activations Density 0.013%

    No Known Activations