© 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. 128877
    Prev
    Next
    INDEX
    Explanations

    terms and phrases associated with wine and its appreciation

    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
    antan
    -0.07
     Coffee
    -0.07
    ì§ĵ
    -0.06
    Coffee
    -0.06
    íĸ
    -0.06
     feed
    -0.06
     oats
    -0.06
    貸
    -0.06
    ække
    -0.06
     feeds
    -0.06
    POSITIVE LOGITS
     wine
    0.15
     wines
    0.14
     Wine
    0.13
     bottle
    0.10
    wine
    0.10
     bottles
    0.10
     grapes
    0.09
     vin
    0.09
     tasting
    0.09
     cork
    0.09
    Activations Density 0.108%

    No Known Activations