© 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. 41121
    Prev
    Next
    INDEX
    Explanations

    references to time durations in recent contexts

    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
    æĸ¹éĿ¢
    -0.07
    ุà¸Ķà¸Ĺ
    -0.07
    resh
    -0.07
    ÂŃi
    -0.06
    175
    -0.06
    uther
    -0.06
    rix
    -0.06
     rodiny
    -0.06
     verze
    -0.06
    111
    -0.06
    POSITIVE LOGITS
     ÙħÛĮÙĦادÛĮ
    0.09
    -prepend
    0.07
    kip
    0.07
    /month
    0.07
    upal
    0.07
     trends
    0.06
    ACP
    0.06
    ucch
    0.06
    inki
    0.06
    PostExecute
    0.06
    Activations Density 0.009%

    No Known Activations