© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 126496
    Prev
    Next
    INDEX
    Explanations

    concepts related to innovation and change in industries

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ATO
    -0.07
    icari
    -0.07
    æĸ½
    -0.07
    frauen
    -0.07
     rew
    -0.07
    ä¼¼
    -0.07
    (æ°´
    -0.07
     Weinstein
    -0.07
    porno
    -0.07
    лиÑĪ
    -0.07
    POSITIVE LOGITS
     manufacturing
    0.07
     production
    0.06
     factory
    0.06
     product
    0.06
     Produkt
    0.06
    lef
    0.06
     Äijá»Ŀi
    0.06
     Manufacturing
    0.06
    325
    0.06
    Factory
    0.06
    Activations Density 0.000%

    No Known Activations