© 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. 30989
    Prev
    Next
    INDEX
    Explanations

    medical center

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is find mentions of medical facility names (e.g., hospitals, medical centers, and health‐care organizations).

    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
     dragging
    -0.07
     Emerald
    -0.06
     vehicle
    -0.06
     viewport
    -0.06
    	status
    -0.06
     posing
    -0.06
    	Version
    -0.06
     Cancel
    -0.06
     cougar
    -0.06
    -0.06
    POSITIVE LOGITS
     rais
    0.06
     참고
    0.06
     quale
    0.06
    cliffe
    0.06
    mite
    0.06
    chied
    0.06
     내용
    0.06
    ylvania
    0.06
     없다
    0.06
    =("
    0.06
    Activations Density 0.031%

    No Known Activations