© 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. 70529
    Prev
    Next
    INDEX
    Explanations

    terms related to royalties and digital rights in contracts

    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
    ington
    -0.07
    linik
    -0.06
    cona
    -0.06
    ugins
    -0.06
    uppy
    -0.06
     Photography
    -0.06
     streak
    -0.06
     probes
    -0.06
    oud
    -0.06
    loff
    -0.05
    POSITIVE LOGITS
     royalty
    0.10
     royalties
    0.08
     music
    0.08
     sublic
    0.08
     song
    0.07
     Roy
    0.07
     copyright
    0.07
    iola
    0.07
     Music
    0.07
    music
    0.07
    Activations Density 0.002%

    No Known Activations