© 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. 1431
    Prev
    Next
    INDEX
    Explanations

    structured information and references to current events or reports

    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
    -pdf
    -0.06
    ,#
    -0.06
    енз
    -0.05
     Cove
    -0.05
    porto
    -0.05
     PDF
    -0.05
    본
    -0.05
     neighboring
    -0.05
    erno
    -0.05
    pdf
    -0.05
    POSITIVE LOGITS
    uard
    0.07
     cá»Ń
    0.07
    illos
    0.07
    ãĤ¹ãĤ¯
    0.07
    ois
    0.06
    Modal
    0.06
    _NOTIFY
    0.06
     WithEvents
    0.06
     âĸ²
    0.06
    Ùĩار
    0.06
    Activations Density 0.060%

    No Known Activations