© 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. 109014
    Prev
    Next
    INDEX
    Explanations

    surgical procedures

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of surgical anatomy and dissection or procedural steps (e.g. anatomical structures and actions like dissecting, mobilizing, preserving).

    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
    umba
    -0.06
     legend
    -0.06
     indictment
    -0.06
    /fonts
    -0.06
    Edition
    -0.06
    _selection
    -0.06
     금
    -0.06
    .hwp
    -0.06
    itus
    -0.06
    .trade
    -0.06
    POSITIVE LOGITS
    PED
    0.07
     scared
    0.07
     incentives
    0.07
     incentive
    0.07
     Beaver
    0.07
     germany
    0.06
     unified
    0.06
    _snap
    0.06
     CREATED
    0.06
     schnell
    0.06
    Activations Density 0.010%

    No Known Activations