© 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. 62206
    Prev
    Next
    INDEX
    Explanations

    references to centers and hubs of various domains, such as economy, culture, education, and politics

    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
    inya
    -0.07
    PixelFormat
    -0.07
    باÙĦ
    -0.07
    æ½
    -0.07
    xac
    -0.07
    aret
    -0.07
    xdb
    -0.07
    rie
    -0.07
    adel
    -0.07
     Zaman
    -0.07
    POSITIVE LOGITS
     activity
    0.09
     hub
    0.08
     hubs
    0.07
     gravity
    0.07
     attention
    0.07
    activity
    0.07
    verse
    0.07
     activities
    0.06
     distribution
    0.06
     where
    0.06
    Activations Density 0.012%

    No Known Activations