© 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. 79197
    Prev
    Next
    INDEX
    Explanations

    references to health-related food and beverages

    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
    _DEPRECATED
    -0.07
    erli
    -0.06
    .IsNullOr
    -0.06
    erre
    -0.06
     subsidi
    -0.06
    uada
    -0.06
    aos
    -0.06
    las
    -0.06
    eward
    -0.06
     гли
    -0.06
    POSITIVE LOGITS
     juice
    0.08
     ju
    0.07
     pulp
    0.07
     Juice
    0.07
    assage
    0.07
    æ¦
    0.07
     Processor
    0.07
     blitz
    0.07
    -thumbnails
    0.07
    ãģıãģł
    0.06
    Activations Density 0.003%

    No Known Activations