© 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. 5-LLAMASCOPE-RES-131K
    11. 125559
    Prev
    Next
    INDEX
    Explanations

    varying forms of the word "accommodate" as well as concepts related to functionality and structure

    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
    eller
    -0.07
    ombo
    -0.06
     Bark
    -0.06
     ward
    -0.06
     Cooke
    -0.06
    lier
    -0.06
    rol
    -0.06
    erin
    -0.06
    .dtd
    -0.06
    лад
    -0.06
    POSITIVE LOGITS
    .gg
    0.09
    enheim
    0.07
    ackets
    0.07
    amp
    0.07
    inear
    0.07
    386
    0.07
    aeda
    0.07
    ettle
    0.07
    osg
    0.06
    peria
    0.06
    Activations Density 0.065%

    No Known Activations