© 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 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. 131006
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate spending time or effort on various activities

    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
    TIM
    -0.08
    ÙĦÛĮسÛĮ
    -0.07
    .TIM
    -0.07
    sik
    -0.06
     Radical
    -0.06
     odpowied
    -0.06
    indow
    -0.06
    avn
    -0.06
    steller
    -0.06
    ervo
    -0.06
    POSITIVE LOGITS
     time
    0.09
     money
    0.07
    efault
    0.07
     Tracker
    0.06
    457
    0.06
    967
    0.06
    ÙĪÙĤت
    0.06
     nights
    0.06
    hone
    0.06
    .time
    0.06
    Activations Density 0.030%

    No Known Activations