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. 85920
    Prev
    Next
    INDEX
    Explanations

    Async

    np_max-act · gemini-2.0-flash

    This neuron fires on occurrences of “async” (in identifiers, keywords, or comments).

    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
     pom
    -0.08
     stamp
    -0.08
     rempl
    -0.07
     dřev
    -0.07
     Sele
    -0.07
     conten
    -0.07
     palms
    -0.07
     mammals
    -0.07
     liver
    -0.07
     rotterdam
    -0.07
    POSITIVE LOGITS
    Async
    0.10
    async
    0.09
    .async
    0.09
     Async
    0.09
    ASY
    0.08
     Andy
    0.08
    .Async
    0.07
     asyncio
    0.07
     async
    0.07
    swick
    0.07
    Activations Density 0.005%

    No Known Activations