© 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 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. 29169
    Prev
    Next
    INDEX
    Explanations

    references to artificial intelligence and voice-activated technologies

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

    Names of virtual assistants, AI systems, and voice technologies (Watson, Alexa, MICA, Audrey, Sophy, voice assistants, etc.) that respond to user commands, provide information, or perform tasks through interfaces like smart speakers.

    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
    resse
    -0.09
    ä¹ĭä¸Ģ
    -0.07
    ussen
    -0.07
     McB
    -0.07
    Ñħи
    -0.07
    важа
    -0.07
    atsby
    -0.07
    Äħ
    -0.07
    unga
    -0.07
    acey
    -0.07
    POSITIVE LOGITS
    -enabled
    0.06
    кÑĥл
    0.06
    -powered
    0.06
     molec
    0.06
    mania
    0.06
    ê°ģ
    0.05
    .respond
    0.05
    /i
    0.05
    acid
    0.05
    prompt
    0.05
    Activations Density 0.002%

    No Known Activations