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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 16553
    Prev
    Next
    INDEX
    Explanations

    coding-related keywords and commands

    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
    Ìģ
    -0.07
    нÑĤ
    -0.07
    oe
    -0.07
    alars
    -0.06
    /***/
    -0.06
    à¸Ļà¹Ĩ
    -0.06
     equally
    -0.06
    lement
    -0.06
    istique
    -0.06
     itself
    -0.06
    POSITIVE LOGITS
    zan
    0.07
    Ĵáŀ
    0.07
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     recap
    0.06
    spam
    0.06
    ieten
    0.06
    تاÙĨ
    0.06
     optionally
    0.06
    indo
    0.06
    UpDown
    0.06
    Activations Density 0.003%

    No Known Activations