© 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. 9-LLAMASCOPE-RES-131K
    11. 96259
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of time and duration

    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
    entin
    -0.06
    icont
    -0.06
     flo
    -0.06
    Îĸ
    -0.06
    .wp
    -0.06
     Rush
    -0.06
    gili
    -0.06
    erville
    -0.06
     же
    -0.06
     mean
    -0.06
    POSITIVE LOGITS
    uries
    0.06
     Lobby
    0.06
    BarButtonItem
    0.06
    pez
    0.06
    .pnl
    0.06
     عص
    0.06
     Annunci
    0.06
     Sanctuary
    0.06
     ëıĻìķĪ
    0.06
    438
    0.06
    Activations Density 0.010%

    No Known Activations