© 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. 5-LLAMASCOPE-RES-131K
    11. 125481
    Prev
    Next
    INDEX
    Explanations

    mentions of conventional practices or systems, particularly in energy and healthcare 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
    سÙĪب
    -0.07
    yer
    -0.07
    son
    -0.07
    unction
    -0.06
    /Library
    -0.06
    \brief
    -0.06
    cad
    -0.06
    /th
    -0.06
    yon
    -0.06
    IDI
    -0.06
    POSITIVE LOGITS
    itzer
    0.07
    heimer
    0.07
    ursed
    0.06
    ä¿Ĺ
    0.06
    izzo
    0.06
    ized
    0.06
     ########.
    0.06
    warf
    0.06
    wealth
    0.06
    ised
    0.06
    Activations Density 0.003%

    No Known Activations