© 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. 15-LLAMASCOPE-RES-131K
    11. 90639
    Prev
    Next
    INDEX
    Explanations

    key elements and structures related to authentication and authorization in programming

    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
    achten
    -0.07
    igaret
    -0.07
    unsch
    -0.07
    apo
    -0.07
    ccoli
    -0.07
    istrovstvÃŃ
    -0.07
    upakan
    -0.06
    rypt
    -0.06
    ieme
    -0.06
    iž
    -0.06
    POSITIVE LOGITS
    _flutter
    0.07
    åıİ
    0.06
     nues
    0.06
     Carp
    0.06
     Rab
    0.06
     ancest
    0.06
    Resize
    0.06
     Rain
    0.06
     burg
    0.06
    üyük
    0.06
    Activations Density 0.059%

    No Known Activations