© 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 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. 131004
    Prev
    Next
    INDEX
    Explanations

    references to weeks and their associated numerical identifiers

    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
     afternoon
    -0.07
    ulg
    -0.06
     morning
    -0.06
    iste
    -0.06
    uil
    -0.06
     conc
    -0.06
     evolved
    -0.06
    anych
    -0.06
     Reyn
    -0.06
    iaux
    -0.06
    POSITIVE LOGITS
     week
    0.11
     Woche
    0.11
     Week
    0.10
     WEEK
    0.09
    Week
    0.09
    -week
    0.09
    åij¨
    0.08
     Wochen
    0.08
    week
    0.08
     Weekly
    0.08
    Activations Density 0.016%

    No Known Activations