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. 43673
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters in the text

    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
     thus
    -0.07
    unya
    -0.07
     such
    -0.07
     other
    -0.07
    'er
    -0.07
     therefore
    -0.06
    thus
    -0.06
    other
    -0.06
     others
    -0.06
     hence
    -0.06
    POSITIVE LOGITS
     Today
    0.14
    Today
    0.13
     today
    0.11
     Following
    0.10
     Leading
    0.10
    today
    0.10
    Leading
    0.10
    ä»Ĭ天
    0.10
     -(
    0.10
     Yesterday
    0.10
    Activations Density 0.021%

    No Known Activations