© 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. 103932
    Prev
    Next
    INDEX
    Explanations

    mentions of Wikimedia and Wikipedia

    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
    UTH
    -0.07
     Aires
    -0.06
    ine
    -0.06
    abinet
    -0.06
    stal
    -0.06
     sao
    -0.06
    los
    -0.06
    731
    -0.06
     thuis
    -0.06
     commute
    -0.06
    POSITIVE LOGITS
     Lara
    0.06
    pyx
    0.06
    IRA
    0.06
    ritch
    0.06
    Caught
    0.06
     Zam
    0.06
     McCl
    0.06
    -services
    0.06
    ÙıÙĩ
    0.06
    endoza
    0.05
    Activations Density 0.001%

    No Known Activations