© 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. 81431
    Prev
    Next
    INDEX
    Explanations

    references to significant events or periods in history

    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
    alim
    -0.07
     Gross
    -0.06
    031
    -0.06
    783
    -0.06
    bos
    -0.06
    Reality
    -0.06
     Fur
    -0.06
    iel
    -0.06
    ınca
    -0.06
     continue
    -0.06
    POSITIVE LOGITS
     unlike
    0.10
     improved
    0.09
     differently
    0.09
    Unlike
    0.08
     Unlike
    0.08
     Improved
    0.08
    ä»Ĭå¹´
    0.08
     mieux
    0.08
     better
    0.07
     ìĿ´ë²Ī
    0.07
    Activations Density 0.043%

    No Known Activations