© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106650
    Prev
    Next
    INDEX
    Explanations

    key events related to restaurant openings

    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
    Ùħت
    -0.06
     increasingly
    -0.06
    ær
    -0.06
     näch
    -0.06
     Roose
    -0.06
    ôn
    -0.06
     åĨĨ
    -0.06
    ania
    -0.06
    yal
    -0.06
     Danh
    -0.06
    POSITIVE LOGITS
    -opening
    0.08
     staffing
    0.07
     inaugural
    0.07
     Doors
    0.07
    opens
    0.07
     opening
    0.07
     doors
    0.07
     preview
    0.07
    opening
    0.07
     debut
    0.07
    Activations Density 0.017%

    No Known Activations