© 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. 15927
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and code elements

    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
    _Parse
    -0.07
     uyar
    -0.07
    ubl
    -0.07
    ãĥ«ãĤ¯
    -0.07
    ÅĻez
    -0.07
    urdu
    -0.07
    iene
    -0.07
     warnings
    -0.07
    EFR
    -0.07
    amet
    -0.07
    POSITIVE LOGITS
     ['.
    0.07
    ÏĦοÏħÏĤ
    0.06
    .hibernate
    0.06
     Mist
    0.06
    ìĽĮíģ¬
    0.06
    vo
    0.06
    sit
    0.06
    uel
    0.06
    001
    0.06
    AreaView
    0.06
    Activations Density 0.004%

    No Known Activations