© 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. 58789
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and structures within equations

    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
     Great
    -0.07
     Eg
    -0.07
     Tal
    -0.07
     eg
    -0.07
    ekil
    -0.06
    ug
    -0.06
     Hal
    -0.06
     Smy
    -0.06
     fro
    -0.06
    adam
    -0.06
    POSITIVE LOGITS
    readcr
    0.08
    terms
    0.07
     TERMS
    0.07
     expression
    0.07
    acen
    0.07
     terms
    0.07
    -expression
    0.07
    æĭ¬
    0.07
    ansom
    0.07
    acas
    0.07
    Activations Density 0.116%

    No Known Activations