© 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. 124442
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional depth and heartfelt sentiments

    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
    estar
    -0.08
    unas
    -0.07
    illard
    -0.07
    illas
    -0.07
    uste
    -0.07
    esso
    -0.07
    èħ¦
    -0.07
    vig
    -0.07
    hazi
    -0.07
    ÃĹ↵↵
    -0.07
    POSITIVE LOGITS
     hearts
    0.07
     Hearts
    0.07
    -heart
    0.07
    .EventQueue
    0.06
    /em
    0.06
    -shaped
    0.06
     valves
    0.06
     contents
    0.06
     shaped
    0.06
    strings
    0.06
    Activations Density 0.020%

    No Known Activations