© 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. 70105
    Prev
    Next
    INDEX
    Explanations

    celestial objects and their characteristics

    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
     Content
    -0.06
    ä½µ
    -0.06
    portlet
    -0.06
    anagan
    -0.06
    blas
    -0.06
    uels
    -0.06
    utzer
    -0.06
    lage
    -0.06
    agi
    -0.06
    elems
    -0.06
    POSITIVE LOGITS
    Magnitude
    0.07
     grad
    0.07
     opak
    0.07
    Unmount
    0.07
    imed
    0.06
    ugal
    0.06
    ndo
    0.06
    ilda
    0.06
     faint
    0.06
     visibility
    0.06
    Activations Density 0.037%

    No Known Activations