© 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. 69222
    Prev
    Next
    INDEX
    Explanations

    references to census data and related statistical information

    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
     EXEMPLARY
    -0.06
    maktan
    -0.06
    éijij
    -0.06
    ãĥ³ãĥĦ
    -0.06
     lip
    -0.06
     Mo
    -0.06
    .plist
    -0.06
     mo
    -0.06
     her
    -0.06
     Medi
    -0.06
    POSITIVE LOGITS
     Census
    0.08
     collectors
    0.07
    pivot
    0.07
     Collector
    0.07
     census
    0.07
     collector
    0.07
    Ïİ
    0.07
    enumerator
    0.07
     statist
    0.06
    persons
    0.06
    Activations Density 0.001%

    No Known Activations