© 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. 106632
    Prev
    Next
    INDEX
    Explanations

    words related to crowd density and venue occupancy

    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
    ãĤ
    -0.07
     Dün
    -0.07
    éli
    -0.07
     aras
    -0.07
    ÑĥмÑĥ
    -0.07
    çŃĴ
    -0.07
    ventus
    -0.06
    bia
    -0.06
    =>$
    -0.06
    culus
    -0.06
    POSITIVE LOGITS
     again
    0.07
     with
    0.07
     its
    0.06
    ará
    0.06
     once
    0.06
     itself
    0.06
     determined
    0.06
     where
    0.06
     Treaty
    0.06
    ammer
    0.06
    Activations Density 0.034%

    No Known Activations