© 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. 17-LLAMASCOPE-RES-131K
    11. 38371
    Prev
    Next
    INDEX
    Explanations

    expressions related to leaving stable employment for a different career path

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ifter
    -0.07
    ebo
    -0.07
    utch
    -0.07
    elves
    -0.06
     cour
    -0.06
    êm
    -0.06
    icio
    -0.06
    ubo
    -0.06
    ighth
    -0.06
    igest
    -0.06
    POSITIVE LOGITS
     conventional
    0.08
    \grid
    0.07
     corpor
    0.07
    èIJ¬
    0.07
     compl
    0.07
    ccion
    0.07
     mainstream
    0.06
     corporate
    0.06
     cush
    0.06
    allo
    0.06
    Activations Density 0.013%

    No Known Activations