© 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. 72657
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time, specifically transitions between different time periods

    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
    esk
    -0.07
    kö
    -0.07
    ounce
    -0.06
    ắt
    -0.06
    hus
    -0.06
    rength
    -0.06
    ecut
    -0.06
    à¹ĥà¸Ļà¸ģาร
    -0.06
    äºļæ´²
    -0.06
    ients
    -0.06
    POSITIVE LOGITS
    934
    0.07
     Scene
    0.07
    ivy
    0.06
     Heard
    0.06
    055
    0.06
    Scene
    0.06
    happy
    0.06
    æļ®
    0.06
    374
    0.06
     happy
    0.06
    Activations Density 0.006%

    No Known Activations