© 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. 91230
    Prev
    Next
    INDEX
    Explanations

    aux

    np_max-act · gemini-2.0-flash

    The neuron fires on C++ Boost.MPL auxiliary header identifiers—i.e. tokens in include-guard macros or #include paths featuring “aux_” in Boost.MPL headers.

    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
     알고
    -0.07
     Zimmerman
    -0.07
    開始
    -0.07
    ीकरण
    -0.06
     tested
    -0.06
    crollView
    -0.06
    andoned
    -0.06
    İstanbul
    -0.06
     شرکت
    -0.06
     پرداخت
    -0.06
    POSITIVE LOGITS
     labeling
    0.07
     responseData
    0.06
     Andr
    0.06
    aux
    0.06
     offered
    0.06
     donor
    0.06
    اشی
    0.06
    EO
    0.06
     synonymous
    0.06
    >>,
    0.06
    Activations Density 0.000%

    No Known Activations