© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 127212
    Prev
    Next
    INDEX
    Explanations

    references to historical periods and dynasties

    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
    ctl
    -0.07
    entai
    -0.07
    оÑĩки
    -0.06
     ÙħستÙĤ
    -0.06
    инг
    -0.06
    amo
    -0.06
    eeee
    -0.06
    okane
    -0.06
    edom
    -0.06
    ä¼
    -0.06
    POSITIVE LOGITS
    -era
    0.12
    era
    0.11
     era
    0.10
     period
    0.10
    /post
    0.09
     Era
    0.09
    -period
    0.09
     dönemde
    0.09
     periodo
    0.08
     ÙħÛĮÙĦادÛĮ
    0.08
    Activations Density 0.011%

    No Known Activations