© 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. 15-LLAMASCOPE-RES-131K
    11. 26758
    Prev
    Next
    INDEX
    Explanations

    terms related to voice control technology and its applications

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

    References to voice recognition technology, speech-to-text services, and voice control systems, often in technical documentation or code examples.

    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
    embr
    -0.07
    encion
    -0.06
    overy
    -0.06
    igroup
    -0.06
    ekl
    -0.06
    ometown
    -0.06
    ipse
    -0.06
    eref
    -0.06
     Viewing
    -0.06
     Jonas
    -0.06
    POSITIVE LOGITS
    LEAR
    0.07
     voice
    0.07
    input
    0.07
     commands
    0.07
     input
    0.07
     Thanh
    0.06
    206
    0.06
    -input
    0.06
    //"
    0.06
    commands
    0.06
    Activations Density 0.016%

    No Known Activations