© 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 EvalsExportsinterp-engineNEWAPI 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. 121175
    Prev
    Next
    INDEX
    Explanations

    references to mathematical equations and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Specialized syntax and notation from technical or mathematical documents, including LaTeX commands, equation references, and formatting markers that typically appear in scientific papers, code documentation, or technical manuals.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    fern
    -0.08
    abar
    -0.06
    ritch
    -0.06
     exclus
    -0.06
    illard
    -0.06
    ãĤ·ãĥªãĥ¼ãĤº
    -0.06
     ApiController
    -0.06
    awah
    -0.06
     zam
    -0.06
    alled
    -0.06
    POSITIVE LOGITS
    jang
    0.07
    tro
    0.06
    ãĥ³ãĥĢ
    0.06
    FIXME
    0.06
     Trang
    0.06
    anza
    0.06
    forge
    0.06
     tro
    0.06
    isko
    0.06
    ali
    0.06
    Activations Density 0.330%

    No Known Activations