© 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. 31567
    Prev
    Next
    INDEX
    Explanations

    terms related to protocols and devices in technical contexts

    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
    raki
    -0.07
     NavParams
    -0.06
     Gre
    -0.05
    ElementException
    -0.05
    æĴ
    -0.05
     tandem
    -0.05
     bearings
    -0.05
    ]âĢı
    -0.05
     lip
    -0.05
     Ble
    -0.05
    POSITIVE LOGITS
    Industrial
    0.09
     Industrial
    0.09
     industrial
    0.09
     Safety
    0.08
    afety
    0.08
     safety
    0.08
     plant
    0.07
    Plant
    0.07
    å·¥ä¸ļ
    0.07
     Plant
    0.07
    Activations Density 0.009%

    No Known Activations