© 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. 3534
    Prev
    Next
    INDEX
    Explanations

    terms related to Greek mythology, specifically characters and events from the Trojan War

    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
     Auschwitz
    -0.07
    ENU
    -0.07
    atism
    -0.07
    andler
    -0.06
     Sphinx
    -0.06
    รà¸ĵ
    -0.06
    trand
    -0.06
    mobx
    -0.06
    åĢĻ
    -0.06
     Lump
    -0.06
    POSITIVE LOGITS
     war
    0.07
    -war
    0.06
     Troy
    0.06
     famously
    0.06
     Rug
    0.06
    kdir
    0.06
     Caucus
    0.06
    -plugins
    0.06
     divine
    0.06
    Plugins
    0.06
    Activations Density 0.002%

    No Known Activations