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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 84390
    Prev
    Next
    INDEX
    Explanations

    brain functions

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of the prefrontal cortex (and nearby regions) in the context of higher‐order, abstract cognitive functions.

    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
     Riv
    -0.07
    IllegalAccessException
    -0.07
     Yue
    -0.06
    ACING
    -0.06
    扬
    -0.06
    _POS
    -0.06
     inconvenience
    -0.06
    디시
    -0.06
     Dodd
    -0.06
    AdapterManager
    -0.06
    POSITIVE LOGITS
    шов
    0.07
     พร
    0.07
    аг
    0.07
     roleName
    0.06
    .abs
    0.06
     ([[
    0.06
    Click
    0.06
    (parsed
    0.06
    \"",
    0.06
    ۲۶
    0.06
    Activations Density 0.038%

    No Known Activations