© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 123654
    Prev
    Next
    INDEX
    Explanations

    terms related to functional beverages and market trends in the beverage industry

    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
    enties
    -0.07
    chine
    -0.06
     Barber
    -0.06
     pros
    -0.06
    rysler
    -0.06
    acket
    -0.06
     Rarity
    -0.06
     Stam
    -0.05
     interdisciplinary
    -0.05
     resource
    -0.05
    POSITIVE LOGITS
     market
    0.10
    .market
    0.08
     category
    0.08
    market
    0.08
    _market
    0.08
     Market
    0.08
    -market
    0.08
     kategor
    0.08
    CategoryId
    0.08
    Market
    0.07
    Activations Density 0.081%

    No Known Activations