© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 71616
    Prev
    Next
    INDEX
    Explanations

    themes related to sadness and tragedy

    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
    èª
    -0.08
    (æ°´
    -0.07
    å«Į
    -0.07
     æĢ
    -0.07
    imary
    -0.07
    mare
    -0.07
    _FF
    -0.06
    alette
    -0.06
    594
    -0.06
     smo
    -0.06
    POSITIVE LOGITS
     sad
    0.07
     life
    0.07
     sighed
    0.07
     loss
    0.07
    æĤ²
    0.06
     sadness
    0.06
     pain
    0.06
    hed
    0.06
    angu
    0.06
     Loss
    0.06
    Activations Density 0.103%

    No Known Activations