© 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 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. 74997
    Prev
    Next
    INDEX
    Explanations

    references to digital resources and online tools related to data and applications

    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
    ä¹ĭä¸Ģ
    -0.07
    /LICENSE
    -0.07
     McB
    -0.06
     Åŀirket
    -0.06
    ỡ
    -0.06
    аÑĪа
    -0.06
    ARRIER
    -0.06
    å±
    -0.06
     cir
    -0.05
    ãģªãģ®
    -0.05
    POSITIVE LOGITS
     platform
    0.08
    GMEM
    0.07
    platform
    0.07
    .Guna
    0.07
     interface
    0.07
    .glob
    0.07
    /WebAPI
    0.07
    км
    0.06
    -Javadoc
    0.06
    arcy
    0.06
    Activations Density 0.037%

    No Known Activations