© 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. 59419
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron responds to segments of fully qualified Java (and similar) package or import namespace identifiers.

    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
     Geneva
    -0.07
     Elf
    -0.07
    textInput
    -0.06
     clients
    -0.06
    ificacion
    -0.06
     fruity
    -0.06
     nues
    -0.06
    ’ex
    -0.06
     sna
    -0.06
     після
    -0.06
    POSITIVE LOGITS
    .This
    0.06
    ;/*
    0.06
    JP
    0.06
    ็ด
    0.06
    _NATIVE
    0.06
     Vaugh
    0.06
    LP
    0.06
     speculative
    0.06
     elev
    0.06
     ****************************************************************************
    0.06
    Activations Density 0.001%

    No Known Activations