© 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. 17-LLAMASCOPE-RES-131K
    11. 72909
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation

    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
    _dependency
    -0.06
    ets
    -0.06
     congratulations
    -0.06
    Congratulations
    -0.06
     Congratulations
    -0.06
    ems
    -0.06
    ensen
    -0.06
    Ìģ
    -0.06
     congrat
    -0.05
     QUICK
    -0.05
    POSITIVE LOGITS
     appreciate
    0.08
     appreciated
    0.08
     Thank
    0.08
    ãĥ³ãĤ¬
    0.07
     Floyd
    0.07
    usat
    0.07
     Apprec
    0.07
     appreciation
    0.07
    uÃŃ
    0.07
    ãģĤãĤĬãģĮãģ¨ãģĨãģĶãģĸ
    0.07
    Activations Density 0.013%

    No Known Activations