© 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. 70468
    Prev
    Next
    INDEX
    Explanations

    terms related to orthopedic surgical systems 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
     ag
    -0.07
    unas
    -0.06
     Agent
    -0.06
     balance
    -0.06
    ansson
    -0.05
    estre
    -0.05
     regime
    -0.05
    Agents
    -0.05
     Bi
    -0.05
     net
    -0.05
    POSITIVE LOGITS
     landmarks
    0.08
    .xyz
    0.07
    ovu
    0.07
    _navigation
    0.07
     движениÑı
    0.07
     Screw
    0.07
     ê°ķëĤ¨
    0.07
     planning
    0.07
     predecess
    0.07
    uben
    0.07
    Activations Density 0.017%

    No Known Activations