© 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. 127647
    Prev
    Next
    INDEX
    Explanations

    terms related to infrastructure projects and developments

    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
     ones
    -0.07
     al
    -0.06
    abad
    -0.06
    æĿ¥çļĦ
    -0.06
     or
    -0.06
     others
    -0.05
     Gratuit
    -0.05
     oneself
    -0.05
     اØ
    -0.05
    Boolean
    -0.05
    POSITIVE LOGITS
    åıĬåħ¶
    0.08
     ÑĪлÑıÑħом
    0.07
    âĢª
    0.07
    InvalidOperationException
    0.06
    panion
    0.06
     ëĦ¤ìĿ´íĬ¸
    0.06
     nouve
    0.06
     обеÑģпеÑĩива
    0.06
    948
    0.06
    HasKey
    0.06
    Activations Density 0.046%

    No Known Activations