© 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. 15-LLAMASCOPE-RES-131K
    11. 87246
    Prev
    Next
    INDEX
    Explanations

    references to classroom activities and educational tasks

    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
    еви
    -0.07
     currentValue
    -0.06
    Unified
    -0.06
     newVal
    -0.06
    isÃŃ
    -0.06
    noc
    -0.06
     Unified
    -0.06
    inka
    -0.06
     ë¨
    -0.06
    illon
    -0.06
    POSITIVE LOGITS
     progress
    0.07
    ãĥ¼ãĥijãĥ¼
    0.06
    sth
    0.06
    entai
    0.06
    itored
    0.06
    å¯Ŀ
    0.06
     Ø¢ÙĨÙĦاÛĮÙĨ
    0.06
    à¸Ńà¸Ńà¸Ļà¹Ħลà¸Ļ
    0.06
     nominal
    0.06
     Progress
    0.06
    Activations Density 0.002%

    No Known Activations