© 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. 2327
    Prev
    Next
    INDEX
    Explanations

    references to the act of grinding or processes related to grinding

    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
    Ãłng
    -0.07
    oss
    -0.07
    otes
    -0.06
    .fs
    -0.06
    chten
    -0.06
     nghá»ģ
    -0.06
    تد
    -0.06
    FI
    -0.06
    jni
    -0.06
    ayment
    -0.06
    POSITIVE LOGITS
    608
    0.07
    /gr
    0.07
    hog
    0.07
    rase
    0.07
     Grinder
    0.07
    edly
    0.06
    æľ«
    0.06
    eri
    0.06
    umbn
    0.06
     Grinding
    0.06
    Activations Density 0.007%

    No Known Activations