© 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. 59491
    Prev
    Next
    INDEX
    Explanations

    terms related to data organization and management in software 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
    ÂŃn
    -0.08
    зÑĭ
    -0.07
    'gc
    -0.07
    оÑĢаз
    -0.07
    -0.07
    ÂŃs
    -0.07
    //{{
    -0.07
    èĬ¸
    -0.07
    /non
    -0.07
    âĢĮâĢĮ
    -0.07
    POSITIVE LOGITS
     etc
    0.16
    etc
    0.12
    çŃī
    0.09
     ëĵ±ìĿĦ
    0.08
    ãģªãģ©
    0.08
     others
    0.07
    ãģªãģ©ãģ®
    0.07
    )
    0.07
     other
    0.07
     ëĵ±ìĿĺ
    0.07
    Activations Density 0.012%

    No Known Activations