© 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. 86402
    Prev
    Next
    INDEX
    Explanations

    significant events or turning points in historical narratives

    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
    има
    -0.08
    kap
    -0.08
    anter
    -0.07
    ickt
    -0.07
    .nano
    -0.07
    unma
    -0.07
     ayrıca
    -0.07
    otten
    -0.07
     ikt
    -0.07
    LinkId
    -0.07
    POSITIVE LOGITS
     within
    0.07
     soon
    0.07
     first
    0.06
    ensch
    0.06
    /Foundation
    0.06
     became
    0.06
     after
    0.06
     obscure
    0.06
    within
    0.05
    xic
    0.05
    Activations Density 0.031%

    No Known Activations