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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58566
    Prev
    Next
    INDEX
    Explanations

    injuries and recovery

    np_max-act · gemini-2.0-flash

    news related to sports injuries.

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

    The neuron detects mentions of sports‐related injuries and their medical details (body parts, procedures, and recovery timelines).

    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
    ,"%
    -0.07
     gum
    -0.07
    _reduction
    -0.06
    щают
    -0.06
    ческим
    -0.06
     nightclub
    -0.06
    ้ร
    -0.06
     Metric
    -0.06
     "%
    -0.06
    ,'%
    -0.06
    POSITIVE LOGITS
     nặng
    0.07
     NAN
    0.07
     *[
    0.06
     Deputy
    0.06
    itates
    0.06
     _|
    0.06
    测试
    0.06
    leri
    0.06
    Tại
    0.06
     pelo
    0.06
    Activations Density 0.025%

    No Known Activations