© 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. 61
    Prev
    Next
    INDEX
    Explanations

    references to software engineering and project work

    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
    avic
    -0.08
    ecn
    -0.07
    hev
    -0.07
     Rubin
    -0.07
    kea
    -0.07
    åħ¬å¼Ģ
    -0.07
    /GPL
    -0.07
    Intialized
    -0.07
    INVAL
    -0.07
    å¼¥
    -0.07
    POSITIVE LOGITS
    485
    0.07
     release
    0.06
     Release
    0.06
     only
    0.06
    á»Ŀ
    0.06
     functional
    0.06
     rollback
    0.06
     branch
    0.06
     dependencies
    0.06
     deploy
    0.06
    Activations Density 0.002%

    No Known Activations