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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 55876
    Prev
    Next
    INDEX
    Explanations

    terms related to remote desktop and application sharing functionalities

    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
    apolis
    -0.07
    ıb
    -0.06
     culo
    -0.06
    licas
    -0.06
    wstring
    -0.06
     society
    -0.06
    apis
    -0.06
    oldur
    -0.06
    (æ°´
    -0.06
    /Dk
    -0.06
    POSITIVE LOGITS
    uter
    0.06
     remotely
    0.06
     live
    0.06
     Assistance
    0.06
     æĤ
    0.06
    IRECT
    0.06
     UserControl
    0.06
     Live
    0.06
     Monter
    0.06
    asco
    0.06
    Activations Density 0.009%

    No Known Activations