© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 130114
    Prev
    Next
    INDEX
    Explanations

    references to wine production and its historical context

    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
    referrer
    -0.07
     Tome
    -0.07
    RefCount
    -0.07
    ádu
    -0.07
    项
    -0.07
    onds
    -0.07
    Fab
    -0.07
     Kraj
    -0.07
     manufactured
    -0.07
     bq
    -0.07
    POSITIVE LOGITS
    Ã
    0.07
     grapes
    0.07
     cu
    0.07
     stre
    0.06
     vines
    0.06
     ter
    0.06
     oak
    0.06
     grape
    0.06
     disg
    0.06
     Gr
    0.06
    Activations Density 0.004%

    No Known Activations