© 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. 9157
    Prev
    Next
    INDEX
    Explanations

    intravenous

    np_max-act · gemini-2.0-flash

    This neuron activates on terms related to medical infusion or feeding systems—particularly intravenous (IV) fluids, infusion sets, and associated equipment.

    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
     هند
    -0.06
    FUN
    -0.06
    데
    -0.06
    Util
    -0.06
    Auto
    -0.06
     Cham
    -0.06
    ilians
    -0.06
    Construct
    -0.06
     Rog
    -0.05
    .req
    -0.05
    POSITIVE LOGITS
     knight
    0.07
     बय
    0.06
     Opinion
    0.06
     вариан
    0.06
     Northern
    0.06
     drip
    0.06
    (scene
    0.06
    amen
    0.06
     radius
    0.06
    isActive
    0.06
    Activations Density 0.009%

    No Known Activations