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. 43387
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical or scientific concepts, including parameters and 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
     addCriterion
    -0.08
    ãĤ¤ãĥ¤
    -0.08
     principalTable
    -0.06
    éru
    -0.06
     Hib
    -0.06
    .AutoComplete
    -0.06
     marketer
    -0.06
     pricing
    -0.06
    æĬķèµĦ
    -0.06
     تØŃÙħÙĬÙĦ
    -0.06
    POSITIVE LOGITS
     f
    0.12
     federal
    0.12
    Shutdown
    0.12
     Shutdown
    0.11
     shutdown
    0.11
     TSA
    0.11
     federally
    0.10
     Federal
    0.10
     unpaid
    0.09
     paycheck
    0.09
    Activations Density 0.007%

    No Known Activations