© 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. 121476
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific cultural references

    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
    оÑģÑĤи
    -0.08
    ardin
    -0.08
    iosper
    -0.07
    ASHBOARD
    -0.07
    .Html
    -0.07
    emean
    -0.07
    uche
    -0.07
    Reader
    -0.07
    arkan
    -0.07
    omor
    -0.07
    POSITIVE LOGITS
     legend
    0.08
     former
    0.08
     colleague
    0.08
     mate
    0.08
    ite
    0.07
     ex
    0.07
     favorite
    0.07
     titan
    0.07
     giant
    0.07
     favourite
    0.06
    Activations Density 0.156%

    No Known Activations