© 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. 90749
    Prev
    Next
    INDEX
    Explanations

    references to collaboration and teamwork in creative processes

    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
    -0.07
    alk
    -0.06
    ç´
    -0.06
    appa
    -0.06
    amer
    -0.06
    raham
    -0.06
     warehouse
    -0.06
     bör
    -0.05
    querque
    -0.05
    hed
    -0.05
    POSITIVE LOGITS
    _exchange
    0.07
     katkı
    0.07
    STYPE
    0.07
    âĢ¦.↵↵
    0.07
    _shared
    0.07
    ä¸Ģ人
    0.07
    antro
    0.07
     злоÑĩ
    0.07
    á»ĭch
    0.07
    νοÏį
    0.07
    Activations Density 0.006%

    No Known Activations