© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 101167
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    C# code snippets involving multi-threading and parallel processing.

    oai_token-act-pair · gpt-4o-mini
    Triggered by @xinyanhu8

    The neuron fires on tokens related to multithreading in code—especially uses of the Thread class, arrays of threads (e.g. “Thread[]”), and thread‐management calls.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    -other
    -0.07
    iev
    -0.07
     chest
    -0.06
     Future
    -0.06
     Idle
    -0.06
    막
    -0.06
     testimon
    -0.06
     prefect
    -0.06
     caul
    -0.06
     functools
    -0.06
    POSITIVE LOGITS
    ction
    0.07
    御
    0.06
    티
    0.06
     orden
    0.06
    IENTATION
    0.06
    ्रध
    0.06
     hier
    0.06
    _native
    0.06
     Automatically
    0.06
    	JSONObject
    0.06
    Activations Density 0.022%

    No Known Activations