© 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. 6251
    Prev
    Next
    INDEX
    Explanations

    Java

    np_max-act · gemini-2.0-flash

    The neuron fires on programming‐language syntax (class/method names, type names, XML tags, code punctuation, etc.), i.e. raw code fragments.

    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
    улю
    -0.06
    сього
    -0.06
    nitř
    -0.06
    ูกค
    -0.06
    89
    -0.06
     fish
    -0.06
     Über
    -0.06
    เตร
    -0.06
     spreadsheet
    -0.06
    Flutter
    -0.06
    POSITIVE LOGITS
    -reaching
    0.06
    Ross
    0.06
     ipAddress
    0.06
    Coord
    0.06
     Boh
    0.06
    골
    0.06
    _Line
    0.06
    Russ
    0.06
     Kos
    0.06
     quello
    0.06
    Activations Density 0.003%

    No Known Activations