© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 47069
    Prev
    Next
    INDEX
    Explanations

    _

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting reStructuredText reference‐target lines—i.e. those “.. _anchor_name:” style definitions that use leading underscores.

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

    content related to documentation and instructions for programming libraries or frameworks.

    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
     tastes
    -0.07
    dispatcher
    -0.07
    _Result
    -0.06
    â
    -0.06
    Graphic
    -0.06
    _COR
    -0.06
     apps
    -0.06
     Apparently
    -0.06
     getters
    -0.06
     attic
    -0.06
    POSITIVE LOGITS
     quantitative
    0.07
     problém
    0.06
    OLDER
    0.06
     incorrect
    0.06
     για
    0.06
    _URI
    0.06
     Coron
    0.06
     ني
    0.06
     mou
    0.06
     agitation
    0.06
    Activations Density 0.000%

    No Known Activations