© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76872
    Prev
    Next
    INDEX
    Explanations

    ()

    np_max-act · gemini-2.0-flash

    The neuron fires on the “()” token of empty parameter lists in C++ function declarations (e.g. the “()” after `main`).

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

    code snippets that demonstrate file input/output operations in C++.

    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
     dohod
    -0.07
     redd
    -0.07
    Jan
    -0.07
    /topic
    -0.06
    David
    -0.06
    蛇
    -0.06
     David
    -0.06
    _SHA
    -0.06
     multiples
    -0.06
    -hero
    -0.06
    POSITIVE LOGITS
    mour
    0.06
     venture
    0.06
    бря
    0.06
    ^K
    0.06
    のが
    0.06
     ingres
    0.06
     axle
    0.06
     provozu
    0.06
    nj
    0.06
     чи
    0.06
    Activations Density 0.016%

    No Known Activations