© 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. 1830
    Prev
    Next
    INDEX
    Explanations

    sentences that indicate a significant narrative or conclusion

    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
    ắp
    -0.07
    enschaft
    -0.07
    aras
    -0.07
    eras
    -0.07
    /helper
    -0.07
    erate
    -0.07
     Developing
    -0.06
    Ú©ÙĦ
    -0.06
     McKenzie
    -0.06
    hart
    -0.06
    POSITIVE LOGITS
     Toe
    0.06
    yntax
    0.06
    OTH
    0.06
    imet
    0.06
     mist
    0.06
    има
    0.06
     Apostle
    0.05
     ÑĦак
    0.05
    otti
    0.05
    omite
    0.05
    Activations Density 0.001%

    No Known Activations