© 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. 40533
    Prev
    Next
    INDEX
    Explanations

    terms associated with uncertainty and variance in scientific data

    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
     bezier
    -0.07
    filesize
    -0.07
    ott
    -0.06
    Bezier
    -0.06
     Sez
    -0.06
    erti
    -0.06
     hire
    -0.06
    erglass
    -0.06
     splits
    -0.06
    bbox
    -0.06
    POSITIVE LOGITS
    [:,:,
    0.09
     map
    0.09
    map
    0.09
     maps
    0.08
     colormap
    0.08
    maps
    0.08
    .colorbar
    0.08
    omap
    0.07
    MAP
    0.07
     surface
    0.07
    Activations Density 0.198%

    No Known Activations