© 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 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. 84297
    Prev
    Next
    INDEX
    Explanations

    references to historical events and political actions related to Vietnam

    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
    atal
    -0.06
    utin
    -0.06
     Yönet
    -0.06
     Dere
    -0.06
     fluffy
    -0.06
     Sheep
    -0.06
     è¢
    -0.06
     Bry
    -0.06
     Raptors
    -0.06
    #
    -0.06
    POSITIVE LOGITS
     Vietnamese
    0.13
     Vietnam
    0.13
     Cambodia
    0.10
    Viet
    0.10
     rice
    0.10
     Viet
    0.09
     Laos
    0.09
     Viá»ĩt
    0.09
    rice
    0.08
     Song
    0.08
    Activations Density 0.058%

    No Known Activations