© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 118309
    Prev
    Next
    INDEX
    Explanations

    terms related to surgical systems and methods, especially those involving joint replacement

    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
     doubly
    -0.06
     breath
    -0.06
    #
    -0.06
     throat
    -0.06
     basal
    -0.06
    umas
    -0.06
     respiratory
    -0.06
     Tie
    -0.06
    ANE
    -0.06
     Spi
    -0.06
    POSITIVE LOGITS
     joint
    0.12
     Joint
    0.10
    joint
    0.10
    Joint
    0.09
     orth
    0.09
    arth
    0.09
     ar
    0.09
     arthritis
    0.09
     Orth
    0.09
     joints
    0.08
    Activations Density 0.069%

    No Known Activations