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. 44217
    Prev
    Next
    INDEX
    Explanations

    complex symbols and notation within texts

    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
     covid
    -0.06
    ieee
    -0.06
     Covid
    -0.06
     Cbd
    -0.06
    EH
    -0.06
    WXYZ
    -0.06
    ESA
    -0.06
     зави
    -0.06
     anz
    -0.06
     cbd
    -0.06
    POSITIVE LOGITS
     LINE
    0.15
    LINE
    0.12
     Line
    0.10
     messaging
    0.09
     Premium
    0.09
    .LINE
    0.09
     users
    0.09
     Korea
    0.09
     Philippines
    0.09
     stickers
    0.09
    Activations Density 0.005%

    No Known Activations