© 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. 17-LLAMASCOPE-RES-131K
    11. 120075
    Prev
    Next
    INDEX
    Explanations

    phrases related to collaboration and innovation within organizations

    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
     nackte
    -0.08
    ä¸Ī
    -0.07
    าะห
    -0.07
    à¸Ħà¹Ĥà¸Ļ
    -0.07
    /Instruction
    -0.07
    cie
    -0.07
    onium
    -0.07
    า
    -0.07
    odon
    -0.07
    _CNTL
    -0.07
    POSITIVE LOGITS
     future
    0.10
     other
    0.09
     new
    0.08
     further
    0.07
     ultimately
    0.07
     additional
    0.07
     novel
    0.07
    .recycle
    0.07
     local
    0.07
    future
    0.07
    Activations Density 0.078%

    No Known Activations