© 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. 92009
    Prev
    Next
    INDEX
    Explanations

    key terms associated with significant cultural events and rituals

    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
    anean
    -0.07
    lotte
    -0.06
    ertext
    -0.06
     Church
    -0.06
    @student
    -0.06
     Dame
    -0.06
    amage
    -0.06
    tering
    -0.06
    =>"
    -0.06
    vi
    -0.06
    POSITIVE LOGITS
     lunar
    0.08
    enberg
    0.08
     festival
    0.07
     moon
    0.07
     Equivalent
    0.07
     equivalent
    0.07
    лÑıн
    0.06
     tiny
    0.06
     banks
    0.06
     festivals
    0.06
    Activations Density 0.002%

    No Known Activations