© 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. 15-LLAMASCOPE-RES-131K
    11. 103344
    Prev
    Next
    INDEX
    Explanations

    mention of dairy products and their market implications

    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
    xic
    -0.07
    ÙĪÙĨ
    -0.06
    ylland
    -0.06
    _site
    -0.06
    xon
    -0.06
     site
    -0.06
    antino
    -0.06
    amento
    -0.06
    emmel
    -0.06
     combustion
    -0.06
    POSITIVE LOGITS
     milk
    0.11
     mil
    0.10
     dairy
    0.09
     sữa
    0.09
     Milky
    0.09
    ä¹³
    0.08
     Milk
    0.08
     lact
    0.08
     nipples
    0.07
     Tanner
    0.07
    Activations Density 0.020%

    No Known Activations