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. 44323
    Prev
    Next
    INDEX
    Explanations

    text related to data structure and organizational formats in documents

    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
    .simps
    -0.05
    ï¼ģ",
    -0.05
    [of
    -0.05
     ê°¤ë¡ľê·¸ë¡ľ
    -0.05
    [OF
    -0.05
     ÚĨت
    -0.05
    ©©
    -0.05
    ?"↵↵↵↵
    -0.05
    ï¼ģãĢį↵↵
    -0.05
     ).↵↵
    -0.05
    POSITIVE LOGITS
    :
    0.40
     :
    0.30
    :↵
    0.29
    :.
    0.27
    ï¼ļ
    0.26
    :_
    0.26
    :The
    0.26
    :**
    0.26
    :"
    0.25
    :[
    0.25
    Activations Density 4.902%

    No Known Activations