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. 44051
    Prev
    Next
    INDEX
    Explanations

    variables and symbols in a mathematical or programming context

    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
    IÃĵN
    -0.06
     UT
    -0.06
    logan
    -0.06
    sparse
    -0.06
    CCR
    -0.06
    odash
    -0.06
     лиÑĨ
    -0.05
     dây
    -0.05
    .misc
    -0.05
     nerd
    -0.05
    POSITIVE LOGITS
     Af
    0.11
    Af
    0.09
     incumb
    0.09
     Crisis
    0.08
     market
    0.08
     markets
    0.08
     crisis
    0.08
     af
    0.08
     competitors
    0.08
     marketplace
    0.07
    Activations Density 0.004%

    No Known Activations