© 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. 82905
    Prev
    Next
    INDEX
    Explanations

    references to wine and its cultural significance

    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
     seins
    -0.08
    fg
    -0.07
    bens
    -0.06
    abant
    -0.06
    icari
    -0.06
    swer
    -0.06
    astos
    -0.06
    kün
    -0.06
    tesy
    -0.06
     Store
    -0.06
    POSITIVE LOGITS
     producers
    0.07
     wines
    0.07
     stylist
    0.07
     ries
    0.07
     produce
    0.06
     disg
    0.06
     producing
    0.06
     output
    0.06
    produce
    0.06
    iles
    0.06
    Activations Density 0.008%

    No Known Activations