© 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. 93926
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to transportation methods and their efficiencies

    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
    mey
    -0.07
     active
    -0.06
    óng
    -0.06
    ativas
    -0.06
    libraries
    -0.06
    ledge
    -0.06
     recycle
    -0.05
    inactive
    -0.05
    plots
    -0.05
    831
    -0.05
    POSITIVE LOGITS
     transport
    0.08
    Genre
    0.07
    andex
    0.07
     Modes
    0.07
    transport
    0.07
    orton
    0.07
     PROT
    0.07
    èĽĽ
    0.07
    askan
    0.06
     Transport
    0.06
    Activations Density 0.018%

    No Known Activations