© 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. 92406
    Prev
    Next
    INDEX
    Explanations

    specific terms related to educational pursuits and certifications

    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
    kü
    -0.06
    Culture
    -0.06
    yahoo
    -0.06
    ucken
    -0.06
    allen
    -0.06
    еÑĢж
    -0.06
    oyo
    -0.06
    rå
    -0.06
    odzi
    -0.06
    ÎŃÏģει
    -0.06
    POSITIVE LOGITS
     you
    0.15
    ä½ł
    0.12
     você
    0.11
     ä½ł
    0.11
    you
    0.11
     bạn
    0.10
     your
    0.10
     YOU
    0.10
     Ø´Ùħا
    0.10
    ï¼Įä½ł
    0.09
    Activations Density 0.033%

    No Known Activations