© 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 EvalsExportsinterp-engineNEWAPI 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. 73643
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and events related to holidays or special days

    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
     season
    -0.07
    ZN
    -0.07
    aleb
    -0.07
     darkness
    -0.07
    _season
    -0.06
    cock
    -0.06
    ÃŃf
    -0.06
     ÏİÏģα
    -0.06
    alama
    -0.06
    Season
    -0.06
    POSITIVE LOGITS
     day
    0.16
     Day
    0.13
     DAY
    0.12
    -day
    0.12
    Day
    0.12
     giorno
    0.11
    .day
    0.11
    DAY
    0.11
     ÙĬÙĪÙħ
    0.11
    day
    0.11
    Activations Density 0.060%

    No Known Activations