© 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. 96017
    Prev
    Next
    INDEX
    Explanations

    terms related to the action of functioning or managing operations

    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
    /ne
    -0.08
    еÑĢÑĪ
    -0.08
    ulle
    -0.07
    ë§IJ
    -0.07
    ukan
    -0.07
    rana
    -0.07
    oice
    -0.07
    OwnerId
    -0.07
    anie
    -0.07
    imei
    -0.07
    POSITIVE LOGITS
    iffer
    0.07
     under
    0.07
     operating
    0.07
    fine
    0.06
     throughout
    0.06
    pace
    0.06
     operate
    0.06
     within
    0.06
     differently
    0.06
     operates
    0.06
    Activations Density 0.012%

    No Known Activations