© 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. 59803
    Prev
    Next
    INDEX
    Explanations

    key terms associated with seasonal changes in food availability

    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
     Weekly
    -0.07
    sched
    -0.06
    Wednesday
    -0.06
     Tuesday
    -0.06
    Friday
    -0.06
     Friday
    -0.06
    Thursday
    -0.06
     Fridays
    -0.06
     åŁ
    -0.06
     Thursday
    -0.06
    POSITIVE LOGITS
     season
    0.22
    -season
    0.19
    season
    0.18
     seasonal
    0.18
     seasons
    0.17
     Season
    0.16
    Season
    0.15
     winter
    0.15
     offseason
    0.15
     sezon
    0.15
    Activations Density 0.288%

    No Known Activations