Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90525
    Prev
    Next
    INDEX
    Explanations

    Mayo

    np_max-act · gemini-2.0-flash

    statistical data and comparisons regarding health risks and medical studies.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron specifically detects occurrences of the proper name “Mayo Clinic.”

    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
    break
    -0.07
    ании
    -0.07
    .food
    -0.07
    リーズ
    -0.06
    �
    -0.06
    igg
    -0.06
    .real
    -0.06
     Vacc
    -0.06
     زنان
    -0.06
    /am
    -0.06
    POSITIVE LOGITS
    ерв
    0.07
     Fargo
    0.07
     fashionable
    0.06
     colossal
    0.06
    Trivia
    0.06
     popped
    0.06
     doctors
    0.06
     ioctl
    0.06
     Link
    0.06
    -employed
    0.06
    Activations Density 0.002%

    No Known Activations