© 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. 108166
    Prev
    Next
    INDEX
    Explanations

    terms related to web application performance and debugging

    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
    éĹ
    -0.07
    ç®Ģåįķ
    -0.07
     simply
    -0.06
     ÙħÙħÚ©ÙĨ
    -0.06
    qui
    -0.06
    may
    -0.06
     Ú¯ÙĪ
    -0.06
    lue
    -0.06
     your
    -0.06
     might
    -0.06
    POSITIVE LOGITS
    orrect
    0.10
     indeed
    0.09
     correctly
    0.09
     correct
    0.09
     successfully
    0.08
    æŃ£ç¡®
    0.07
    correct
    0.07
     correctamente
    0.07
    _correct
    0.07
    æŃ£å¸¸
    0.07
    Activations Density 0.016%

    No Known Activations