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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 130347
    Prev
    Next
    INDEX
    Explanations

    asynchronous

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect mentions of asynchronous programming concepts.

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

    asynchronous programming concepts and implementations.

    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
     scars
    -0.06
    lene
    -0.06
    /portfolio
    -0.06
    	diff
    -0.06
    得
    -0.06
    "Some
    -0.06
    ku
    -0.06
    _dic
    -0.06
     mile
    -0.06
    สม
    -0.06
    POSITIVE LOGITS
     waveform
    0.09
     asynchronous
    0.08
     Сер
    0.07
     рів
    0.07
     Hin
    0.07
    дром
    0.07
    ocurrency
    0.06
     inté
    0.06
    untary
    0.06
     шляхом
    0.06
    Activations Density 0.004%

    No Known Activations