© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98409
    Prev
    Next
    INDEX
    Explanations

    terms related to regulatory compliance and categorization

    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
    \Migration
    -0.07
    ician
    -0.07
    irc
    -0.07
    .RichTextBox
    -0.07
    uten
    -0.07
    aland
    -0.07
    anza
    -0.07
    edin
    -0.07
    .TabControl
    -0.07
    äng
    -0.07
    POSITIVE LOGITS
    راÙĨÛĮ
    0.06
    веÑģÑĤи
    0.05
     unc
    0.05
    culo
    0.05
     aerial
    0.05
     Transit
    0.05
     Rede
    0.05
     pret
    0.05
     Kits
    0.05
     embed
    0.05
    Activations Density 0.037%

    No Known Activations