© 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. 15695
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal rights and licensing agreements

    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
    midi
    -0.07
    omon
    -0.07
    erus
    -0.07
    elon
    -0.07
    erable
    -0.07
    ura
    -0.07
    ocket
    -0.07
    hora
    -0.07
    amon
    -0.07
     киÑĪ
    -0.07
    POSITIVE LOGITS
     either
    0.07
     rights
    0.07
    quer
    0.07
     any
    0.06
     sag
    0.06
     ownership
    0.06
     nor
    0.06
     sinon
    0.06
    ught
    0.06
     permission
    0.06
    Activations Density 0.001%

    No Known Activations