© 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. 89796
    Prev
    Next
    INDEX
    Explanations

    conjunctions linking clauses or 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
    urma
    -0.08
     ÑĥÑģ
    -0.07
    aea
    -0.07
    ych
    -0.07
    usan
    -0.07
    oleÄį
    -0.07
    licken
    -0.07
    byn
    -0.07
     aforementioned
    -0.07
    zcze
    -0.06
    POSITIVE LOGITS
     intuit
    0.06
     semi
    0.06
    ButtonType
    0.06
    quartered
    0.06
     ones
    0.06
     fr
    0.06
     surpr
    0.05
    ATTER
    0.05
    inton
    0.05
    ãģĴ
    0.05
    Activations Density 0.000%

    No Known Activations