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. 11486
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols, parameters, and technical terms related to optimization and uncertainty quantification

    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
    adelphia
    -0.07
    à¥įâĢį
    -0.07
    ë¡Ŀ
    -0.06
    onu
    -0.06
     Prediction
    -0.06
    akis
    -0.06
     пÑĢоÑĢ
    -0.06
    otec
    -0.06
    ledon
    -0.06
    ì»
    -0.06
    POSITIVE LOGITS
     blogging
    0.17
     bloggers
    0.16
     blogger
    0.15
     Blogger
    0.14
     monet
    0.13
     blog
    0.13
     Blog
    0.12
    -blog
    0.11
     readers
    0.11
     blogs
    0.11
    Activations Density 0.004%

    No Known Activations