© 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 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. 75083
    Prev
    Next
    INDEX
    Explanations

    patents related to medical devices and surgical 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
    edo
    -0.07
     Press
    -0.07
    uint
    -0.06
    rell
    -0.06
    JUST
    -0.06
    uxtap
    -0.06
     interpersonal
    -0.06
    oldem
    -0.06
    //{{
    -0.06
    ctp
    -0.05
    POSITIVE LOGITS
    jian
    0.07
    eb
    0.07
    ires
    0.07
    æ·
    0.07
    eeper
    0.06
    iÃŁ
    0.06
    ä¸ĭ载次æķ°
    0.06
    Ľå»º
    0.06
    ãĥ¼ãĥ
    0.06
     vur
    0.06
    Activations Density 0.025%

    No Known Activations