© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98971
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "sake" indicating a purpose or reason behind actions

    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
    sel
    -0.08
    ised
    -0.07
     mell
    -0.06
    kle
    -0.06
    pp
    -0.06
    anga
    -0.06
    /or
    -0.06
    lod
    -0.06
     Hudson
    -0.06
    nee
    -0.06
    POSITIVE LOGITS
     sake
    0.09
    esterday
    0.07
    #__
    0.07
    \common
    0.07
    åįĵ
    0.07
    :Get
    0.07
    feit
    0.07
    両
    0.06
    ocache
    0.06
    .UIManager
    0.06
    Activations Density 0.006%

    No Known Activations