© 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. 5386
    Prev
    Next
    INDEX
    Explanations

    references to community involvement and social connections

    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
    овеÑĢ
    -0.07
    ấu
    -0.07
    ivre
    -0.07
    anke
    -0.07
    ¥IJ
    -0.07
    efa
    -0.07
    ilmington
    -0.07
    elib
    -0.06
    ihan
    -0.06
    YK
    -0.06
    POSITIVE LOGITS
     biod
    0.06
     tasks
    0.06
     depend
    0.06
     mutual
    0.06
     ë´ī
    0.06
     mÃŃnimo
    0.06
     dependent
    0.06
    536
    0.06
     mutually
    0.06
    ift
    0.06
    Activations Density 0.001%

    No Known Activations