© 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. 128461
    Prev
    Next
    INDEX
    Explanations

    references to language-related topics and systems

    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
    ãĥ¼ãĥĵ
    -0.08
    /Dk
    -0.07
    ikes
    -0.07
    mlink
    -0.07
    ÅĽnie
    -0.07
    asha
    -0.07
    .twimg
    -0.07
    translated
    -0.07
    .addHandler
    -0.07
    æĿī
    -0.07
    POSITIVE LOGITS
     worldwide
    0.08
     official
    0.07
    人åı£
    0.07
     æ³
    0.06
     dia
    0.06
     speakers
    0.06
     spread
    0.06
     population
    0.06
     wherever
    0.06
     Guar
    0.06
    Activations Density 0.007%

    No Known Activations