© 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. 69731
    Prev
    Next
    INDEX
    Explanations

    references to system commands and user permissions in a computing context

    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
    ngen
    -0.08
    fitness
    -0.07
    holm
    -0.07
    oblin
    -0.07
    reed
    -0.07
    759
    -0.06
     expiresIn
    -0.06
    温
    -0.06
    ÑĮко
    -0.06
     å·
    -0.06
    POSITIVE LOGITS
     ownership
    0.09
    ê¶Į
    0.09
     grant
    0.08
     privilege
    0.08
     privileges
    0.08
     permission
    0.08
    æĿĥéĻIJ
    0.08
     grants
    0.08
     authority
    0.07
     privileged
    0.07
    Activations Density 0.009%

    No Known Activations