© 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. 15-LLAMASCOPE-RES-131K
    11. 86002
    Prev
    Next
    INDEX
    Explanations

    logistical processes and inventory management concepts

    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
    ve
    -0.06
    ain
    -0.06
    eli
    -0.06
     simple
    -0.06
     fool
    -0.06
     Cain
    -0.06
    inth
    -0.05
     key
    -0.05
     Sie
    -0.05
     brave
    -0.05
    POSITIVE LOGITS
     batch
    0.10
    batch
    0.10
    æī¹
    0.09
    ãģ¾ãģ¨
    0.09
     Batch
    0.09
     BATCH
    0.09
    Batch
    0.09
    744
    0.09
     batches
    0.08
    .batch
    0.08
    Activations Density 0.023%

    No Known Activations