© 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. 5186
    Prev
    Next
    INDEX
    Explanations

    terms that relate to integration and collaboration across various fields and sectors

    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
    esso
    -0.07
    ommen
    -0.07
    ISCO
    -0.07
    etto
    -0.07
    vik
    -0.07
    BlockSize
    -0.07
     merk
    -0.07
    rlen
    -0.07
    ocode
    -0.07
    REA
    -0.06
    POSITIVE LOGITS
     across
    0.08
     existing
    0.07
     various
    0.07
    ä¸įåIJĮ
    0.06
     traditional
    0.06
     expertise
    0.06
     multiple
    0.06
    ventional
    0.06
     different
    0.06
     complementary
    0.06
    Activations Density 0.026%

    No Known Activations