© 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. 79729
    Prev
    Next
    INDEX
    Explanations

    temporal markers related to days, weeks, and months

    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
     ´
    -0.06
     prosec
    -0.06
    isy
    -0.06
    Ìģ
    -0.06
    GMEM
    -0.06
    ени
    -0.06
    assen
    -0.06
    ırak
    -0.06
    sing
    -0.06
    267
    -0.06
    POSITIVE LOGITS
    's
    0.14
    ’s
    0.12
    çļĦ
    0.11
    ìĿĺ
    0.09
    ãģ®
    0.08
    çļĦæĥħ
    0.08
    çļĦ大
    0.08
    çļĦå¿ĥ
    0.08
    çļĦå°ı
    0.08
    ãģ®å¤§
    0.07
    Activations Density 0.016%

    No Known Activations