Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43553
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables in technical or academic text

    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
     freshwater
    -0.06
    afc
    -0.05
    ãĤ¦ãĤ©
    -0.05
     MIPS
    -0.05
    ippy
    -0.05
     Fisheries
    -0.05
     congratulate
    -0.05
     tươi
    -0.05
    .arc
    -0.05
     Arap
    -0.05
    POSITIVE LOGITS
     dinners
    0.13
     supper
    0.13
     pop
    0.12
     Dinner
    0.11
     din
    0.11
     dinner
    0.11
     chef
    0.10
     popup
    0.10
     event
    0.10
     Din
    0.10
    Activations Density 0.006%

    No Known Activations