© 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. 6187
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    references to debugging files and patch notes related to coding or software development.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron is detecting Git diff/patch header metadata—e.g. the “b/…” file‐path marker, the “index” line with hash ranges (“..”), and related file‐mode tokens.

    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
     مان
    -0.07
     Crow
    -0.06
    anager
    -0.06
    _latest
    -0.06
    Tube
    -0.06
    aland
    -0.06
    sten
    -0.06
     갖
    -0.06
     Caps
    -0.06
    Were
    -0.06
    POSITIVE LOGITS
    sb
    0.07
     ابو
    0.07
    .getToken
    0.06
    visibility
    0.06
     sod
    0.06
     keyCode
    0.06
    nee
    0.06
     OUR
    0.06
    \core
    0.06
    izontally
    0.06
    Activations Density 0.001%

    No Known Activations