© 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. 82359
    Prev
    Next
    INDEX
    Explanations

    references to economic and cultural significance related to cities and their attractions

    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
    (æĹ¥
    -0.08
     VÅ¡ech
    -0.07
    arem
    -0.07
     (('
    -0.07
     Blasio
    -0.07
    İ·
    -0.07
    ConfigurationException
    -0.07
    znik
    -0.07
    Ñĭл
    -0.07
    issant
    -0.07
    POSITIVE LOGITS
     many
    0.09
     both
    0.09
     several
    0.08
     some
    0.08
     fewer
    0.07
     a
    0.07
     numerous
    0.06
     one
    0.06
     only
    0.06
    hani
    0.06
    Activations Density 0.011%

    No Known Activations