© 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. 42564
    Prev
    Next
    INDEX
    Explanations

    category and classification labels

    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
    edes
    -0.08
    erdem
    -0.07
    éļĨ
    -0.07
    ophobia
    -0.07
    forcement
    -0.07
    eref
    -0.07
    odie
    -0.07
    еÑĤе
    -0.07
    bote
    -0.07
    GD
    -0.07
    POSITIVE LOGITS
    serter
    0.07
    teg
    0.06
     gl
    0.06
    Utc
    0.06
    /format
    0.06
    teki
    0.06
    388
    0.06
     ê²°
    0.06
     gn
    0.06
    ItemSelectedListener
    0.06
    Activations Density 0.000%

    No Known Activations