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

    Neuronpedia

    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. 87962
    Prev
    Next
    INDEX
    Explanations

    commands and definitions in programming or scripting contexts

    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
    incy
    -0.09
     ↵↵
    -0.08
    #
    -0.08
    ali
    -0.08
    printStats
    -0.07
    çī§
    -0.07
    anchor
    -0.07
    /Dk
    -0.07
    inci
    -0.07
    Slf
    -0.07
    POSITIVE LOGITS
     v
    0.07
     s
    0.07
     al
    0.06
     tmp
    0.06
     ret
    0.06
    643
    0.06
    96
    0.06
     m
    0.06
    828
    0.05
     n
    0.05
    Activations Density 0.015%

    No Known Activations