© 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 EvalsExportsinterp-engineNEWAPI 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. 89384
    Prev
    Next
    INDEX
    Explanations

    geographic locations and facilities related to business operations

    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
    eways
    -0.08
    /Instruction
    -0.08
     adulte
    -0.07
    pecies
    -0.07
    Č↵
    -0.07
    ãĢĢãĤ¤
    -0.07
    ÅĻi
    -0.07
    aidu
    -0.07
    lemn
    -0.07
    ternet
    -0.07
    POSITIVE LOGITS
     industrial
    0.11
     Industrial
    0.10
     manufacturing
    0.08
     warehouse
    0.08
     facility
    0.08
    Industrial
    0.08
     factory
    0.08
     plant
    0.07
     ware
    0.07
     factories
    0.07
    Activations Density 0.029%

    No Known Activations