© 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. 41547
    Prev
    Next
    INDEX
    Explanations

    complex code structures and terminology

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

    Special characters or sequences that serve as syntax markers in programming code, markup languages, and formatted documents.

    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
    åıİ
    -0.07
    ssc
    -0.07
    >NN
    -0.07
    اÛĮÛĮ
    -0.07
    ascal
    -0.07
    acct
    -0.07
     tôn
    -0.07
    aspers
    -0.06
    xis
    -0.06
     Dün
    -0.06
    POSITIVE LOGITS
    0.06
    ug
    0.06
    oui
    0.06
    )application
    0.06
     spect
    0.06
    alon
    0.06
    },{↵
    0.05
    andal
    0.05
    .GetLength
    0.05
    otech
    0.05
    Activations Density 0.002%

    No Known Activations