© 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. 71321
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement and gratitude related to current events

    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
    otten
    -0.07
     ðŁĻĤ↵↵
    -0.06
    -<?
    -0.06
    ibel
    -0.06
    .''↵↵
    -0.06
    .hs
    -0.05
    kách
    -0.05
     veter
    -0.05
    ToolBar
    -0.05
    icha
    -0.05
    POSITIVE LOGITS
     @
    0.11
     &
    0.11
    &amp
    0.09
     pic
    0.09
     tomorrow
    0.08
     #
    0.08
    ERRU
    0.08
     (@
    0.08
     &↵
    0.08
    .@
    0.07
    Activations Density 0.054%

    No Known Activations