© 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. 108866
    Prev
    Next
    INDEX
    Explanations

    conjunctions and their usage in connecting phrases and ideas

    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
    endar
    -0.07
     Mang
    -0.07
    pst
    -0.06
     ble
    -0.06
    odesk
    -0.06
    ãĥĪãĥ«
    -0.06
    lej
    -0.06
    verse
    -0.06
    emark
    -0.06
    uger
    -0.06
    POSITIVE LOGITS
    ØŃد
    0.07
    ãĤ¹ãĤ«
    0.07
    IDI
    0.07
     deren
    0.07
    berapa
    0.07
     OTHERWISE
    0.07
    amon
    0.06
    Truthy
    0.06
    çļĦå£°éŁ³
    0.06
     processData
    0.06
    Activations Density 0.067%

    No Known Activations