© 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. 17-LLAMASCOPE-RES-131K
    11. 2339
    Prev
    Next
    INDEX
    Explanations

    conjunctions and their usage in connecting ideas

    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
    ục
    -0.07
    hoe
    -0.06
    idor
    -0.06
    ä¸īå¹´
    -0.06
    zel
    -0.06
    ousse
    -0.06
    .mousePosition
    -0.06
    оло
    -0.06
     Lexer
    -0.06
    Trader
    -0.06
    POSITIVE LOGITS
     others
    0.07
     former
    0.07
     erst
    0.07
    urance
    0.06
    .Metro
    0.06
    855
    0.06
    Subscribe
    0.06
    atem
    0.06
     fellow
    0.06
    noch
    0.06
    Activations Density 0.029%

    No Known Activations