© 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. 89287
    Prev
    Next
    INDEX
    Explanations

    terms related to categorization and classification within research or statistical data

    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
    yi
    -0.07
    ÏĥÏħ
    -0.06
     numbering
    -0.06
    esome
    -0.06
    iquid
    -0.06
     latin
    -0.06
     processes
    -0.06
     Death
    -0.06
    istra
    -0.06
    ibold
    -0.06
    POSITIVE LOGITS
    æĮī
    0.09
     từng
    0.09
    ë³Ħ
    0.08
     åIJĦ
    0.08
     separately
    0.08
     æĮ
    0.08
     specific
    0.08
    specific
    0.08
    _specific
    0.08
     regional
    0.08
    Activations Density 0.108%

    No Known Activations