© 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. 7501
    Prev
    Next
    INDEX
    Explanations

    peripheral

    np_max-act · gemini-2.0-flash

    This neuron primarily detects the word “peripheral,” especially in contexts like “peripheral blood.”

    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
     женщина
    -0.07
     laws
    -0.07
     runs
    -0.07
     Legendary
    -0.06
     NOTE
    -0.06
     ise
    -0.06
     revelation
    -0.06
     House
    -0.06
    tea
    -0.06
     run
    -0.06
    POSITIVE LOGITS
     peripheral
    0.08
     Serg
    0.07
    ріп
    0.06
    lä
    0.06
    uard
    0.06
    hm
    0.06
     Τι
    0.06
    website
    0.06
    /interface
    0.06
    ılığ
    0.06
    Activations Density 0.002%

    No Known Activations