© 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. 29107
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and constructs indicative of advanced mathematical or physical theories

    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
     Norris
    -0.07
    kou
    -0.07
     Chuck
    -0.07
    solete
    -0.06
     geile
    -0.06
    kul
    -0.06
    olynomial
    -0.06
    oze
    -0.06
    oup
    -0.06
    kf
    -0.06
    POSITIVE LOGITS
    .Net
    0.07
    ota
    0.07
    ivan
    0.07
    ëĿ¼ëıĦ
    0.06
    ATO
    0.06
    adr
    0.06
     Frid
    0.06
    à¥įà¤Łà¤®
    0.06
    اÙĨÙĩ
    0.06
    arter
    0.06
    Activations Density 0.199%

    No Known Activations