© 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. 58989
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the concept of "days."

    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
     year
    -0.08
     HOUR
    -0.07
     day
    -0.07
     hour
    -0.07
     bot
    -0.07
    ech
    -0.06
    hour
    -0.06
     moment
    -0.06
    ä¸Ģå¹´
    -0.06
     Hour
    -0.06
    POSITIVE LOGITS
    ìĶ©
    0.08
     ago
    0.08
    /month
    0.08
    ãĥ³ãĤº
    0.07
    à¹Ģศษ
    0.07
    Ú¯ÛĮ
    0.07
    ãģĨãģ¡
    0.07
    dirty
    0.07
    amber
    0.07
    .week
    0.07
    Activations Density 0.022%

    No Known Activations