© 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. 42763
    Prev
    Next
    INDEX
    Explanations

    phrases indicating finality or a concluding moment

    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
    reet
    -0.07
    etten
    -0.07
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    -0.06
    ua
    -0.06
    .Directory
    -0.06
     mặt
    -0.06
    Intent
    -0.06
    plan
    -0.06
    éĢģæĸĻçĦ¡æĸĻ
    -0.06
    onus
    -0.06
    POSITIVE LOGITS
     final
    0.09
    -final
    0.08
    final
    0.08
     remaining
    0.08
     Remaining
    0.08
     before
    0.08
    FINAL
    0.08
     hur
    0.07
     FINAL
    0.07
    -push
    0.07
    Activations Density 0.019%

    No Known Activations