© 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 EvalsExportsinterp-engineNEWAPI 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. 107416
    Prev
    Next
    INDEX
    Explanations

    references to significant news events or cultural discussions

    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
    imp
    -0.07
    ample
    -0.06
    ose
    -0.06
     ions
    -0.06
    act
    -0.06
     icing
    -0.06
    öm
    -0.06
    ise
    -0.06
     Protector
    -0.06
     ind
    -0.06
    POSITIVE LOGITS
    licken
    0.07
    veis
    0.07
    TRACE
    0.07
     Ù¾ÛĮØ´ÛĮÙĨÙĩ
    0.07
    afia
    0.07
    ĵn
    0.07
    еÑĢин
    0.07
     åIJįçĦ¡ãģĹ
    0.06
    ìĦ¸ëĮĢ
    0.06
    spender
    0.06
    Activations Density 0.053%

    No Known Activations