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. 44021
    Prev
    Next
    INDEX
    Explanations

    formatting and structural elements of documents, especially in relation to equations and figures

    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
    â̦and
    -0.05
    .::.::
    -0.05
     geile
    -0.05
    ï¼ıï¼ıï¼ıï¼ıï¼ıï¼ıï¼ıï¼ı
    -0.05
    âĻĢâĻĢ
    -0.05
     (“
    -0.05
    Ùijر
    -0.05
    ãeste
    -0.04
    |(↵
    -0.04
    üçük
    -0.04
    POSITIVE LOGITS
     -
    0.35
     -(
    0.29
     -.
    0.27
     -↵
    0.26
     -,
    0.25
     –
    0.25
     -$
    0.25
     `-
    0.24
    -
    0.24
     âĪĴ
    0.24
    Activations Density 3.672%

    No Known Activations