© 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. 103255
    Prev
    Next
    INDEX
    Explanations

    various aspects related to handmade or artisanal products

    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
     especially
    -0.07
     thanks
    -0.06
     either
    -0.06
     [
    -0.06
     or
    -0.06
     if
    -0.06
    åIJ§
    -0.06
    egas
    -0.06
     ox
    -0.06
     (
    -0.06
    POSITIVE LOGITS
     nên
    0.14
    æīĢ以
    0.13
    ï¼ĮæīĢ以
    0.12
     takže
    0.12
     therefore
    0.11
     поÑįÑĤомÑĥ
    0.11
     donc
    0.11
     ÙĦذا
    0.11
     hence
    0.10
     wiÄĻc
    0.10
    Activations Density 0.174%

    No Known Activations