© 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. 84998
    Prev
    Next
    INDEX
    Explanations

    references to social and economic statistics

    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
     discrepan
    -0.07
    ÑĤÑİ
    -0.07
    GBP
    -0.07
    кÑĤÑĥ
    -0.07
    /ca
    -0.07
    elerik
    -0.06
     ÙħØ·
    -0.06
    arger
    -0.06
    วà¸Ļ
    -0.06
     ?><?
    -0.06
    POSITIVE LOGITS
     counted
    0.08
    ince
    0.08
     accounted
    0.08
    ukes
    0.07
     count
    0.07
    INCLUDE
    0.07
     counting
    0.07
     separately
    0.06
     reported
    0.06
     estimate
    0.06
    Activations Density 0.028%

    No Known Activations