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. 43529
    Prev
    Next
    INDEX
    Explanations

    numeric or symbolic representations 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
     https
    -0.08
    â̝
    -0.08
    202
    -0.08
    =https
    -0.07
    https
    -0.07
     COVID
    -0.07
     âģ
    -0.07
     Covid
    -0.07
     coronavirus
    -0.07
     ðĿ
    -0.07
    POSITIVE LOGITS
     Reactive
    0.11
     reactive
    0.10
     Defensive
    0.10
    /react
    0.10
    react
    0.10
     react
    0.10
    -react
    0.09
     proactive
    0.09
    React
    0.09
     defensively
    0.09
    Activations Density 0.003%

    No Known Activations