© 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. 88959
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Spr" and its variations related to growth or sprouting

    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
    'gc
    -0.08
    coder
    -0.07
    ech
    -0.07
    bour
    -0.07
    ioned
    -0.07
    endir
    -0.07
    emas
    -0.07
    ymes
    -0.07
    ensis
    -0.06
    .Automation
    -0.06
    POSITIVE LOGITS
    ague
    0.09
    licht
    0.08
    les
    0.07
    ERO
    0.07
    dzi
    0.07
     convers
    0.07
    kle
    0.07
    uhl
    0.06
     Spr
    0.06
     ÄĮes
    0.06
    Activations Density 0.007%

    No Known Activations