© 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. 88729
    Prev
    Next
    INDEX
    Explanations

    references to cultural events and milestones

    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
    onga
    -0.07
     empty
    -0.06
     newly
    -0.06
    -empty
    -0.06
    afs
    -0.06
     involved
    -0.06
     recently
    -0.06
     downs
    -0.06
     newest
    -0.06
     عÙĤ
    -0.06
    POSITIVE LOGITS
    201
    0.07
     "'.$
    0.07
    hem
    0.06
    root
    0.06
    ç«ĭãģ¦
    0.06
    лÑĮ
    0.06
    /gpl
    0.06
     programm
    0.06
    730
    0.06
     bindActionCreators
    0.06
    Activations Density 0.004%

    No Known Activations