© 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. 82169
    Prev
    Next
    INDEX
    Explanations

    terms related to high-energy physics and quantum systems

    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
     Mass
    -0.06
    enty
    -0.06
    IGNAL
    -0.06
    -dismiss
    -0.06
     Farm
    -0.06
     Ferr
    -0.06
    ambre
    -0.06
    ÙĪÙģ
    -0.06
     Hang
    -0.06
     *&
    -0.06
    POSITIVE LOGITS
    SSH
    0.07
    UIScrollView
    0.07
    valuator
    0.06
    .espresso
    0.06
    èĪĮ
    0.06
     fj
    0.06
    752
    0.06
     Torah
    0.06
    Ñģе
    0.06
     élect
    0.06
    Activations Density 0.052%

    No Known Activations