© 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. 15-LLAMASCOPE-RES-131K
    11. 87000
    Prev
    Next
    INDEX
    Explanations

    elements related to celebration and tributes

    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
    æĹĹ
    -0.07
    ñana
    -0.07
    олиÑĤ
    -0.07
    Äħż
    -0.07
     bande
    -0.07
     buc
    -0.07
    кид
    -0.07
    ç½
    -0.06
    êu
    -0.06
    Ñģим
    -0.06
    POSITIVE LOGITS
    emax
    0.07
     speech
    0.07
     custom
    0.06
    ç¿Ķ
    0.06
     delivery
    0.06
     audience
    0.06
     Fle
    0.06
     performance
    0.06
    pch
    0.06
    villa
    0.06
    Activations Density 0.010%

    No Known Activations