© 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. 29023
    Prev
    Next
    INDEX
    Explanations

    phrases related to racing and competition

    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
    usra
    -0.07
    lenme
    -0.07
    apo
    -0.07
    modele
    -0.07
     Floral
    -0.07
    ascar
    -0.07
    thetic
    -0.07
    ials
    -0.07
    ạch
    -0.06
    ازÛĮ
    -0.06
    POSITIVE LOGITS
    Quotes
    0.06
     Team
    0.06
    :params
    0.06
    quotes
    0.06
    ned
    0.06
     Quotes
    0.06
     Weather
    0.06
     quot
    0.06
    ansa
    0.06
    ãĥ³ãĥĸ
    0.06
    Activations Density 0.011%

    No Known Activations