© 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. 30819
    Prev
    Next
    INDEX
    Explanations

    promotional content related to wine tasting experiences and events

    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
    essler
    -0.07
    aires
    -0.06
    marvin
    -0.06
    iw
    -0.06
    веÑī
    -0.06
    alli
    -0.06
     ActionResult
    -0.06
    ishes
    -0.05
    sect
    -0.05
     Fountain
    -0.05
    POSITIVE LOGITS
     wine
    0.09
     vine
    0.09
     Wine
    0.08
    wine
    0.08
     wines
    0.08
    produ
    0.08
    PDO
    0.07
    production
    0.07
     vines
    0.07
     win
    0.07
    Activations Density 0.022%

    No Known Activations