© 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. 118696
    Prev
    Next
    INDEX
    Explanations

    terms related to mining and ore extraction processes

    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
    wind
    -0.07
    771
    -0.06
     Cra
    -0.06
    iod
    -0.06
     worrying
    -0.06
     Tud
    -0.06
    853
    -0.06
    ettes
    -0.06
    661
    -0.06
    852
    -0.06
    POSITIVE LOGITS
     Feed
    0.08
    Feed
    0.08
     flotation
    0.08
    -feed
    0.07
     Fro
    0.07
    feed
    0.07
     feed
    0.07
     Crushing
    0.07
    浪
    0.07
     Ney
    0.07
    Activations Density 0.027%

    No Known Activations