© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 54001
    Prev
    Next
    INDEX
    Explanations

    punctuations and structural elements in the text

    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
    uzzi
    -0.08
    onga
    -0.08
    ço
    -0.08
    SCII
    -0.07
    uzz
    -0.07
    aurus
    -0.07
    shall
    -0.07
    unken
    -0.07
    ont
    -0.07
    æŀľ
    -0.07
    POSITIVE LOGITS
     Overall
    0.11
     overall
    0.11
    Overall
    0.10
    Conclusion
    0.10
     Conclusion
    0.09
     Bottom
    0.09
     conclusion
    0.09
     bottom
    0.08
    Bottom
    0.07
     concludes
    0.07
    Activations Density 0.004%

    No Known Activations