© 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. 59936
    Prev
    Next
    INDEX
    Explanations

    references to vaccine distribution and bilateral relations

    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
    swick
    -0.08
    íĬ
    -0.08
    ëıĮ
    -0.07
     Ấ
    -0.07
    spb
    -0.07
    ãĥĭãĥĥãĤ¯
    -0.07
    aż
    -0.07
    itm
    -0.07
    ä¸Ģç§į
    -0.07
    ENARIO
    -0.07
    POSITIVE LOGITS
    apa
    0.07
     visa
    0.07
    US
    0.07
    amba
    0.07
     US
    0.07
     Americans
    0.07
     American
    0.07
    1
    0.06
     Embassy
    0.06
    U
    0.06
    Activations Density 0.177%

    No Known Activations