© 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. 119959
    Prev
    Next
    INDEX
    Explanations

    events and activities related to community festivals and 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
    zhou
    -0.07
    rote
    -0.07
    .nih
    -0.06
     Funeral
    -0.06
    æļ®
    -0.06
    cestor
    -0.06
    .github
    -0.06
    oyo
    -0.06
     Rencontre
    -0.06
     Birthday
    -0.06
    POSITIVE LOGITS
    ä»Ĭå¹´
    0.08
     event
    0.08
     exercise
    0.07
    EventArgs
    0.07
     INLINE
    0.07
    erek
    0.06
     annually
    0.06
    ico
    0.06
    ory
    0.06
    ook
    0.06
    Activations Density 0.039%

    No Known Activations