© 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. 129901
    Prev
    Next
    INDEX
    Explanations

    skin

    np_max-act · gemini-2.0-flash

    The neuron detects terms referring to surgical procedures—especially words around incisions (e.g., “skin,” “incision,” “open-heart,” etc.).

    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
     Deadly
    -0.06
     Actress
    -0.06
     Hex
    -0.06
    Writer
    -0.06
    DSL
    -0.06
    flag
    -0.06
     ріш
    -0.06
    érc
    -0.06
     arterial
    -0.06
     düğ
    -0.06
    POSITIVE LOGITS
    اة
    0.07
    .pos
    0.07
     mid
    0.06
    BEL
    0.06
    buy
    0.06
     confined
    0.06
    Mike
    0.06
     الي
    0.06
    .team
    0.06
     تاثیر
    0.06
    Activations Density 0.206%

    No Known Activations