© 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. 94990
    Prev
    Next
    INDEX
    Explanations

    terms related to collagen and extracellular matrix in a medical context

    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
     hete
    -0.06
    jsp
    -0.06
     Pow
    -0.06
    åĪ·
    -0.06
    lector
    -0.06
    ubs
    -0.06
    bart
    -0.06
    inqu
    -0.06
    andest
    -0.06
    adle
    -0.06
    POSITIVE LOGITS
     matrix
    0.08
     Matrix
    0.08
     collagen
    0.08
     fib
    0.07
    herits
    0.07
    Matrix
    0.07
     matrices
    0.07
     repar
    0.07
     ker
    0.07
    matrix
    0.07
    Activations Density 0.013%

    No Known Activations