© 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. 41630
    Prev
    Next
    INDEX
    Explanations

    references to library activities and book borrowing

    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
    ppo
    -0.07
    ptest
    -0.07
    downloads
    -0.06
    _cached
    -0.06
    iliz
    -0.06
    åĭŁ
    -0.06
    ιν
    -0.06
    toc
    -0.06
    å±
    -0.06
    çek
    -0.06
    POSITIVE LOGITS
    adel
    0.08
     circulation
    0.07
    .library
    0.07
     library
    0.07
    -return
    0.07
    (library
    0.07
     Extend
    0.07
    \Lib
    0.07
     return
    0.07
     Library
    0.07
    Activations Density 0.003%

    No Known Activations