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

    Neuronpedia

    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. 28406
    Prev
    Next
    INDEX
    Explanations

    terms related to optical and semiconductor technologies

    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
     Sunder
    -0.07
    irit
    -0.07
     quần
    -0.07
     Sheldon
    -0.06
    abin
    -0.06
    innacle
    -0.06
    aste
    -0.06
    terra
    -0.06
    emetery
    -0.06
    ermen
    -0.06
    POSITIVE LOGITS
     Optical
    0.12
     optical
    0.12
     optics
    0.10
     Laser
    0.08
     laser
    0.08
     metro
    0.08
     grat
    0.08
     lasers
    0.08
     coherent
    0.08
    metro
    0.08
    Activations Density 0.011%

    No Known Activations