© 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. 59401
    Prev
    Next
    INDEX
    Explanations

    _HPP

    np_max-act · gemini-2.0-flash

    This neuron activates on C++ header‐file identifiers, especially tokens like “.hpp” and include‐guard macros ending in “_HPP.”

    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
    CellStyle
    -0.06
     mů
    -0.06
    _both
    -0.06
     pouco
    -0.06
    ukan
    -0.06
     odpad
    -0.06
    unt
    -0.06
     Links
    -0.06
     buffering
    -0.06
     punt
    -0.06
    POSITIVE LOGITS
    _HPP
    0.07
    _family
    0.07
    форм
    0.07
     hoàn
    0.07
    .ImageIcon
    0.07
     Hok
    0.06
    ipay
    0.06
    aveled
    0.06
    erve
    0.06
    PN
    0.06
    Activations Density 0.001%

    No Known Activations