© 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. 82225
    Prev
    Next
    INDEX
    Explanations

    events related to celebrations or gatherings

    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
    ůr
    -0.07
    Ñģли
    -0.07
     ÑģÑħод
    -0.07
    %X
    -0.07
    /sdk
    -0.07
    umbn
    -0.07
     offsetof
    -0.06
     gsi
    -0.06
    vez
    -0.06
     Trades
    -0.06
    POSITIVE LOGITS
     fireworks
    0.10
     py
    0.08
     viewing
    0.07
     Viewing
    0.07
     fired
    0.07
    /fire
    0.07
     Fired
    0.06
     fire
    0.06
     Crack
    0.06
     Stuff
    0.06
    Activations Density 0.003%

    No Known Activations