© 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. 27218
    Prev
    Next
    INDEX
    Explanations

    references to emotions and personal feelings regarding experiences

    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
     tropical
    -0.07
     Tamil
    -0.06
    quit
    -0.06
     Tropical
    -0.06
     Detroit
    -0.06
     Indones
    -0.06
     Oak
    -0.06
    DT
    -0.06
    à¯ģ
    -0.06
     Coastal
    -0.06
    POSITIVE LOGITS
     Tibetan
    0.12
     Tibet
    0.12
    èĹı
    0.10
     Everest
    0.09
    à½
    0.09
     Mongolia
    0.08
     Kashmir
    0.08
     McMahon
    0.08
     Lama
    0.08
     Himal
    0.07
    Activations Density 0.083%

    No Known Activations