© 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. 107359
    Prev
    Next
    INDEX
    Explanations

    actions and events involving motion or impact

    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
    輪
    -0.07
    ahir
    -0.06
    erd
    -0.06
     bottoms
    -0.06
    èįī
    -0.06
    á»Ŀ
    -0.06
     bottom
    -0.06
    ئة
    -0.06
    .Down
    -0.06
    athi
    -0.06
    POSITIVE LOGITS
    deal
    0.07
     catapult
    0.07
    apult
    0.06
    osate
    0.06
    LIKELY
    0.06
    Ñĥда
    0.06
    asel
    0.06
    ãĤ¤ãĤº
    0.06
     @}
    0.06
     gal
    0.06
    Activations Density 0.023%

    No Known Activations