© 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. 93872
    Prev
    Next
    INDEX
    Explanations

    programming-related phrases and keywords that indicate constraints or legacy code

    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
    æľ¯
    -0.07
    æ¸Ī
    -0.07
    Schedulers
    -0.07
     WCHAR
    -0.07
    /Layout
    -0.06
    ãģŁãģ¡ãģ¯
    -0.06
    itori
    -0.06
    аÑĦ
    -0.06
    DataTask
    -0.06
    ÎŁÎ¹
    -0.06
    POSITIVE LOGITS
    ramid
    0.08
    HEST
    0.07
     internal
    0.07
    kova
    0.07
     rare
    0.07
    tern
    0.06
    елиÑĩ
    0.06
     convenience
    0.06
     backward
    0.06
     saat
    0.06
    Activations Density 0.031%

    No Known Activations