© 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. 82389
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and expressions, particularly involving inequalities and norms

    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
    ër
    -0.07
    ault
    -0.07
    ÅĽ
    -0.07
     Nej
    -0.06
    iana
    -0.06
    zan
    -0.06
    ographically
    -0.06
    lisi
    -0.06
    thumbs
    -0.06
    terminal
    -0.06
    POSITIVE LOGITS
    çĭIJ
    0.07
    \<^
    0.07
    oned
    0.07
    467
    0.07
    ups
    0.07
    شد
    0.07
    ned
    0.06
    Telegram
    0.06
    lÃŃn
    0.06
    -UA
    0.06
    Activations Density 0.176%

    No Known Activations