© 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 EvalsExportsinterp-engineNEWAPI 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. 123951
    Prev
    Next
    INDEX
    Explanations

    references to quantity or amounts in a context involving waste management or organization

    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
    emer
    -0.07
    icken
    -0.07
    ÑĮ
    -0.07
    turnstile
    -0.06
    oras
    -0.06
    imer
    -0.06
    æŁIJ
    -0.06
    åIJĦç§į
    -0.06
    assic
    -0.06
    ographics
    -0.06
    POSITIVE LOGITS
    /all
    0.12
     sclerosis
    0.10
     times
    0.07
     dozen
    0.07
     vezes
    0.07
    aret
    0.07
    人çļĦ
    0.07
     occasions
    0.07
     sorts
    0.06
     of
    0.06
    Activations Density 0.012%

    No Known Activations