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. 40506
    Prev
    Next
    INDEX
    Explanations

    API response handling

    np_max-act · gemini-2.0-flash

    This neuron activates on C# API call chains—especially async methods (e.g. methods ending in “Async” or uses of “.Result”)—i.e. it’s looking for asynchronous method invocations in code.

    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
    ////
    -0.07
    
    -0.07
    ắn
    -0.06
    ische
    -0.06
    出口
    -0.06
     πε
    -0.06
     Von
    -0.06
    ्ध
    -0.06
    errs
    -0.06
    είται
    -0.06
    POSITIVE LOGITS
     February
    0.06
    Render
    0.06
    mentioned
    0.06
    .training
    0.06
     ADVISED
    0.06
     originated
    0.06
    -name
    0.06
     attracted
    0.06
    _Print
    0.06
    CppClass
    0.06
    Activations Density 0.011%

    No Known Activations