© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6419
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    This neuron fires on the formal patent‐citation language that introduces and describes prior‐art references (e.g. “U.S. Pat. No. … illustrates/describes an …”).

    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
     source
    -0.07
     kia
    -0.07
    Pros
    -0.07
    $key
    -0.06
     лише
    -0.06
    /books
    -0.06
     Printed
    -0.06
     zich
    -0.06
     declines
    -0.06
     disastrous
    -0.06
    POSITIVE LOGITS
    _RESERVED
    0.07
    عکس
    0.06
     Logan
    0.06
    ร
    0.06
    силь
    0.06
     »,
    0.06
    เป
    0.06
    stdexcept
    0.06
    -sub
    0.06
     [`
    0.06
    Activations Density 0.008%

    No Known Activations