© 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. 120839
    Prev
    Next
    INDEX
    Explanations

    terms related to resting or taking a break

    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
    aho
    -0.09
    enco
    -0.08
    ertz
    -0.07
    emo
    -0.07
    amo
    -0.07
    abaj
    -0.06
    utra
    -0.06
    ergic
    -0.06
     moi
    -0.06
    byss
    -0.06
    POSITIVE LOGITS
    /rest
    0.09
    orative
    0.08
    udy
    0.07
    گاÙĩ
    0.07
    ulet
    0.07
     Gel
    0.07
    ifs
    0.07
    (rest
    0.07
    ikt
    0.07
    ocker
    0.06
    Activations Density 0.010%

    No Known Activations