© 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. 15-LLAMASCOPE-RES-131K
    11. 1202
    Prev
    Next
    INDEX
    Explanations

    references to temporal or duration-related concepts

    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
    λον
    -0.08
    ometown
    -0.07
    rett
    -0.07
    athom
    -0.06
    ÂĢ
    -0.06
    IfExists
    -0.06
    ertia
    -0.06
    еÑĩ
    -0.06
    grp
    -0.06
     Herz
    -0.06
    POSITIVE LOGITS
     duration
    0.11
     until
    0.10
     Duration
    0.10
     longer
    0.10
    -duration
    0.09
     Ùħدت
    0.09
    à¸Ļาà¸Ļ
    0.09
    Ùħدة
    0.09
    æľŁéĸĵ
    0.09
     durations
    0.09
    Activations Density 0.184%

    No Known Activations