© 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. 55554
    Prev
    Next
    INDEX
    Explanations

    expressions related to seasonal changes in nature

    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
    airs
    -0.08
    orners
    -0.08
    idges
    -0.08
    aises
    -0.07
    addock
    -0.07
    ç¯ī
    -0.07
    omite
    -0.07
    essler
    -0.07
    exus
    -0.07
    etch
    -0.07
    POSITIVE LOGITS
     fall
    0.09
    Fall
    0.08
     autumn
    0.08
     Fall
    0.08
     color
    0.08
     Autumn
    0.07
     leaves
    0.07
     FALL
    0.07
     fallen
    0.07
    fall
    0.07
    Activations Density 0.015%

    No Known Activations