© 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. 41068
    Prev
    Next
    INDEX
    Explanations

    phrases related to user authorization and application access issues

    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
    gor
    -0.07
    sut
    -0.07
     Bauer
    -0.06
     sm
    -0.06
     disorder
    -0.06
    eti
    -0.06
     flexGrow
    -0.06
    sm
    -0.06
     impro
    -0.06
     Freed
    -0.06
    POSITIVE LOGITS
    usercontent
    0.09
     ë´
    0.07
     consent
    0.07
    scopes
    0.07
    .oauth
    0.07
    weis
    0.07
     scopes
    0.07
    æİ
    0.06
    .Scope
    0.06
    riminator
    0.06
    Activations Density 0.007%

    No Known Activations