© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 88769
    Prev
    Next
    INDEX
    Explanations

    mentions of updates or new versions of products or systems

    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
    Å¡nÃŃ
    -0.07
    odzi
    -0.06
    agon
    -0.06
    iÅŁim
    -0.06
    ymoon
    -0.06
    ombo
    -0.06
    ана
    -0.06
    ackages
    -0.06
    aÄĩ
    -0.06
     isFirst
    -0.06
    POSITIVE LOGITS
     also
    0.13
    also
    0.10
    Also
    0.10
     ayrıca
    0.10
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.10
     cũng
    0.09
     Also
    0.09
    ä¹Łæľī
    0.09
     other
    0.08
     ãģĿãģ®ä»ĸ
    0.08
    Activations Density 0.017%

    No Known Activations