© 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. 123895
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming utilities and methods

    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
     Baum
    -0.07
    ãĥ¼ãĥķ
    -0.06
    XmlElement
    -0.06
    bai
    -0.06
    enou
    -0.06
     گردÛĮد
    -0.06
    aab
    -0.06
    rips
    -0.06
    Contours
    -0.06
    Decoder
    -0.06
    POSITIVE LOGITS
     utilities
    0.09
     misc
    0.08
     utility
    0.07
     utils
    0.07
    utilities
    0.07
    à¥įसर
    0.07
    Utility
    0.07
    Utilities
    0.07
     miscellaneous
    0.07
     FileUtils
    0.07
    Activations Density 0.023%

    No Known Activations