© 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. 58900
    Prev
    Next
    INDEX
    Explanations

    references to opera performances and festivals

    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
    atik
    -0.07
     Lama
    -0.07
    ember
    -0.07
    adiator
    -0.07
    ieve
    -0.07
    SizePolicy
    -0.06
    iesel
    -0.06
     automát
    -0.06
    úÄįast
    -0.06
    eling
    -0.06
    POSITIVE LOGITS
     oper
    0.11
     OPER
    0.09
     opera
    0.09
     Opera
    0.08
     Oper
    0.08
     Resident
    0.07
    ovsky
    0.07
     commission
    0.07
    rias
    0.07
     lib
    0.07
    Activations Density 0.047%

    No Known Activations