© 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 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. 88613
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "in the" as well as its variations and usage contexts

    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
    oret
    -0.08
    otle
    -0.07
    herits
    -0.07
    Cpp
    -0.07
    ustin
    -0.07
    oooooooo
    -0.07
    orem
    -0.07
    oretical
    -0.07
    SGlobal
    -0.06
    æĸ¹éĿ¢
    -0.06
    POSITIVE LOGITS
     previous
    0.07
     earlier
    0.07
     successful
    0.07
     by
    0.07
    oons
    0.06
    ceb
    0.06
     oleh
    0.06
     millions
    0.06
     Wid
    0.06
    /by
    0.06
    Activations Density 0.094%

    No Known Activations