© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1511
    Prev
    Next
    INDEX
    Explanations

    symbols and notations commonly used in mathematical or statistical contexts

    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
     nues
    -0.07
    indow
    -0.07
     perfectly
    -0.06
     really
    -0.06
    -Sah
    -0.06
     gross
    -0.06
    /non
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
    marvin
    -0.06
     fully
    -0.06
    POSITIVE LOGITS
    овиÑĩ
    0.08
    GINE
    0.07
     phóng
    0.07
    ẩm
    0.07
    ï¼Ĭ
    0.07
    êµIJ
    0.07
    itel
    0.07
    âĢ¦âĢ¦ãĢĤ
    0.07
    ë¡ľëĤĺ
    0.07
    resse
    0.07
    Activations Density 0.000%

    No Known Activations