© 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. 76744
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and syntactical structures in code snippets

    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
    ãĥ¼ãĥª
    -0.06
    hait
    -0.06
    hong
    -0.06
    hoff
    -0.06
    anyl
    -0.06
     Servlet
    -0.06
    rell
    -0.06
     rencont
    -0.06
     stall
    -0.06
    ebra
    -0.06
    POSITIVE LOGITS
     Silver
    0.08
    xaf
    0.08
    .aspx
    0.08
     Guid
    0.08
    .dll
    0.07
    .tt
    0.07
     comparer
    0.07
    Comparer
    0.07
     Win
    0.07
    namespace
    0.07
    Activations Density 0.649%

    No Known Activations