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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6932
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash

    This neuron detects bibliographic reference markers—journal/book names, volume/issue numbers, years, page ranges, and related citation punctuation.

    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
    getClass
    -0.07
     جز
    -0.07
    _dept
    -0.07
    <!--[
    -0.07
    &uuml
    -0.06
     니
    -0.06
    BCM
    -0.06
    consider
    -0.06
    .def
    -0.06
    property
    -0.06
    POSITIVE LOGITS
     violin
    0.07
     Scripture
    0.06
    izzes
    0.06
     drifting
    0.06
    势
    0.06
    developers
    0.06
     Architects
    0.06
    ̀
    0.06
     Short
    0.06
    uştur
    0.06
    Activations Density 0.018%

    No Known Activations