© 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 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. 17-LLAMASCOPE-RES-131K
    11. 125596
    Prev
    Next
    INDEX
    Explanations

    elements and descriptors related to coffee and its associated products

    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
     hungry
    -0.07
    -0.07
     hum
    -0.06
     Plugin
    -0.06
     tr
    -0.06
     cle
    -0.06
    hung
    -0.06
     model
    -0.05
     MVP
    -0.05
     carc
    -0.05
    POSITIVE LOGITS
     tea
    0.13
     coffee
    0.13
     caffeine
    0.12
    coffee
    0.12
     cups
    0.11
    Coffee
    0.11
     caffe
    0.11
    tea
    0.11
     Coffee
    0.10
     Tea
    0.10
    Activations Density 0.044%

    No Known Activations