© 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. 18823
    Prev
    Next
    INDEX
    Explanations

    technical elements or attributes related to document structure and content type

    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
    arp
    -0.07
    pects
    -0.07
     sno
    -0.06
    ected
    -0.06
    etin
    -0.06
    engo
    -0.06
     squ
    -0.06
    bove
    -0.06
    inar
    -0.06
    iban
    -0.06
    POSITIVE LOGITS
    лÑĸÑĤ
    0.07
    .bs
    0.07
    istring
    0.07
    venir
    0.06
    ÙĦÙģ
    0.06
    ÑĭÑĪ
    0.06
    ouri
    0.06
    tz
    0.06
    ones
    0.06
    кÑĢаÑĹ
    0.06
    Activations Density 0.000%

    No Known Activations