© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 83598
    Prev
    Next
    INDEX
    Explanations

    references to Korean cuisine and dining experiences

    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
     actionTypes
    -0.07
    ISP
    -0.06
    DRV
    -0.06
    -envelope
    -0.06
    ruz
    -0.06
    ysi
    -0.06
    EIF
    -0.06
    intersection
    -0.06
    ovu
    -0.06
     unified
    -0.06
    POSITIVE LOGITS
     Shared
    0.10
     sharing
    0.09
    /shared
    0.09
     shared
    0.09
     Sharing
    0.09
    -sharing
    0.09
    Sharing
    0.09
    shared
    0.09
    -shared
    0.08
    _shared
    0.08
    Activations Density 0.047%

    No Known Activations