© 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. 57314
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related terms

    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
     dán
    -0.09
    ulen
    -0.09
    arih
    -0.09
    UNET
    -0.09
     PROCUREMENT
    -0.08
    utron
    -0.08
    ylim
    -0.08
     eskort
    -0.08
     treff
    -0.08
    cheng
    -0.08
    POSITIVE LOGITS
    âĢ¦↵
    0.06
     [
    0.06
     Wings
    0.06
    âĢª
    0.05
     Hart
    0.05
     some
    0.05
     cou
    0.05
     blah
    0.05
    âĢ¦”
    0.05
     I
    0.05
    Activations Density 0.033%

    No Known Activations