© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 62425
    Prev
    Next
    INDEX
    Explanations

    expressions of emotions and personal reflections related to experiences in the arts and creativity

    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
    antan
    -0.08
    Ħ
    -0.07
    irable
    -0.07
    aar
    -0.07
    ample
    -0.07
    bidden
    -0.07
     Schwarz
    -0.07
    اع
    -0.06
    azu
    -0.06
    Ã¤ÃŁ
    -0.06
    POSITIVE LOGITS
     feedback
    0.08
     viewers
    0.08
     audience
    0.07
    -feedback
    0.07
     viewer
    0.07
     customers
    0.07
    feedback
    0.07
     Feedback
    0.07
    pline
    0.07
     Viewer
    0.07
    Activations Density 0.069%

    No Known Activations