© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 126666
    Prev
    Next
    INDEX
    Explanations

    references to sports and athletes, particularly in a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¥
    -0.07
    imax
    -0.06
     Russell
    -0.06
    ÅĤu
    -0.06
    urt
    -0.06
    /slick
    -0.06
    ÃŃk
    -0.06
    asley
    -0.06
    azzi
    -0.06
     Rockies
    -0.06
    POSITIVE LOGITS
     eoq
    0.07
    ÏĦÏĤ
    0.07
    SetActive
    0.06
    bette
    0.06
     íĭ
    0.06
    ombine
    0.06
    ypse
    0.06
    ModifiedDate
    0.06
     ydk
    0.06
     JAXBElement
    0.06
    Activations Density 0.006%

    No Known Activations