© 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. 17-LLAMASCOPE-RES-131K
    11. 58609
    Prev
    Next
    INDEX
    Explanations

    structured output, particularly in the context of scientific results or conclusions

    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
     Schn
    -0.08
    缣
    -0.07
    asm
    -0.07
    SKTOP
    -0.06
     Sachs
    -0.06
    SSERT
    -0.06
     dikke
    -0.06
    edla
    -0.06
     Lang
    -0.06
     Strikes
    -0.06
    POSITIVE LOGITS
     RESULTS
    0.08
    .Results
    0.08
    Conclusion
    0.08
    RESULTS
    0.08
    Results
    0.07
    enco
    0.07
     results
    0.07
    arResult
    0.06
    results
    0.06
     conclusion
    0.06
    Activations Density 0.004%

    No Known Activations