© 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. 86290
    Prev
    Next
    INDEX
    Explanations

    terms related to blood vessels and vascular-related topics

    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
    verbatim
    -0.07
    hab
    -0.07
    turnstile
    -0.07
     trai
    -0.07
    irm
    -0.07
    uty
    -0.07
    artz
    -0.07
    criptor
    -0.07
    isy
    -0.07
    visitor
    -0.07
    POSITIVE LOGITS
    /tree
    0.07
    lined
    0.06
    oven
    0.06
    LT
    0.06
     interiors
    0.06
    ijk
    0.06
     Dit
    0.06
     branches
    0.06
    ·
    0.06
    way
    0.06
    Activations Density 0.009%

    No Known Activations