© 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. 15557
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical properties and environmental impacts

    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
    logan
    -0.07
    antity
    -0.07
    alse
    -0.07
    nowled
    -0.07
     ÑĤи
    -0.07
    itmap
    -0.07
     hopefully
    -0.06
     bufsize
    -0.06
    essages
    -0.06
    ysl
    -0.06
    POSITIVE LOGITS
    anes
    0.08
     ASTM
    0.07
     Crowley
    0.07
     table
    0.06
     Table
    0.06
     chart
    0.06
     properties
    0.06
     Chart
    0.06
    932
    0.06
    /misc
    0.06
    Activations Density 0.010%

    No Known Activations