© 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. 56357
    Prev
    Next
    INDEX
    Explanations

    organizations and community

    np_max-act · gemini-2.0-flash

    This neuron detects technical terms related to health and clinical research contexts (e.g., clinical, care, facilities, incidence, management, public, organizational, professional, policies).

    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
    '])){
    -0.06
    _excel
    -0.06
     Лю
    -0.06
    Any
    -0.06
     Obtain
    -0.06
    Education
    -0.06
     premier
    -0.06
     finalize
    -0.06
    Flutter
    -0.06
     faker
    -0.06
    POSITIVE LOGITS
     uintptr
    0.07
     Caught
    0.06
    bell
    0.06
     immersion
    0.06
    /language
    0.06
    -from
    0.06
    だと
    0.06
    uelve
    0.06
    "=>"
    0.06
    Streaming
    0.06
    Activations Density 0.393%

    No Known Activations