© 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. 15-LLAMASCOPE-RES-131K
    11. 88205
    Prev
    Next
    INDEX
    Explanations

    phrases related to 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
    Å¡et
    -0.07
    .Pixel
    -0.07
    heels
    -0.06
    zano
    -0.06
    _MASK
    -0.06
    amt
    -0.06
    loub
    -0.06
    dana
    -0.06
    à¥ģà¤Ń
    -0.06
    Ø´ÙħاÙĦÛĮ
    -0.06
    POSITIVE LOGITS
     migrationBuilder
    0.07
    oku
    0.07
    isman
    0.07
    ushi
    0.06
    itoris
    0.06
     cps
    0.06
    olle
    0.06
    otime
    0.06
    iskey
    0.06
    atti
    0.06
    Activations Density 0.000%

    No Known Activations