© 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. 104881
    Prev
    Next
    INDEX
    Explanations

    references to years and specific events

    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
    aria
    -0.07
    -0.06
     r
    -0.06
    ãģĵãģĿ
    -0.06
    afe
    -0.06
    uder
    -0.05
    iment
    -0.05
    æĽ¸é¤¨
    -0.05
    hoa
    -0.05
    308
    -0.05
    POSITIVE LOGITS
    references
    0.08
     References
    0.07
     references
    0.07
    ÙħÛĮÙĦ
    0.07
    References
    0.07
    oola
    0.07
    -fontawesome
    0.07
    yms
    0.07
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.07
    osl
    0.07
    Activations Density 0.004%

    No Known Activations