© 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. 108035
    Prev
    Next
    INDEX
    Explanations

    phrases that denote conditions or actions that could be tied to obligations or requirements

    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
    Ã
    -0.07
    ÑĩаÑģÑĤ
    -0.07
    perience
    -0.06
    atable
    -0.06
    isinde
    -0.06
    artment
    -0.06
    icip
    -0.06
    aller
    -0.06
    /****************************************************************************
    -0.06
    alink
    -0.06
    POSITIVE LOGITS
    yal
    0.06
     Dun
    0.06
     suggested
    0.06
     cons
    0.06
    ipers
    0.06
    WER
    0.06
     بÙĪابة
    0.06
    .fm
    0.06
    оÑıн
    0.06
    //"
    0.06
    Activations Density 0.047%

    No Known Activations