© 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. 128217
    Prev
    Next
    INDEX
    Explanations

    key moments of defensive plays in sports

    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
    809
    -0.07
    loub
    -0.07
    alach
    -0.07
    wan
    -0.07
    posix
    -0.07
    ESH
    -0.07
    stÃŃ
    -0.07
     sẵn
    -0.07
    ãĤ´ãĥª
    -0.07
    å¼¥
    -0.07
    POSITIVE LOGITS
     save
    0.08
     saves
    0.08
     Saves
    0.07
     saving
    0.07
     Saved
    0.07
     saved
    0.07
     Save
    0.07
    uy
    0.07
     counter
    0.06
    Save
    0.06
    Activations Density 0.011%

    No Known Activations