© 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. 15-LLAMASCOPE-RES-131K
    11. 26542
    Prev
    Next
    INDEX
    Explanations

    references to physical spaces or locations

    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
    Kit
    -0.07
    fall
    -0.07
    arten
    -0.07
    zell
    -0.06
    cko
    -0.06
    太éĥİ
    -0.06
    zelf
    -0.06
    392
    -0.06
     prosec
    -0.06
     Chips
    -0.06
    POSITIVE LOGITS
    .dm
    0.07
    Msp
    0.07
     Zucker
    0.07
    eprom
    0.06
     area
    0.06
    olon
    0.06
    stru
    0.06
    stdafx
    0.06
     Singleton
    0.06
     اصÙĦÛĮ
    0.06
    Activations Density 0.027%

    No Known Activations