© 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 EvalsExportsinterp-engineNEWAPI 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. 54963
    Prev
    Next
    INDEX
    Explanations

    information related to logistical operations and supplies

    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
     commuter
    -0.08
     opin
    -0.07
     commuters
    -0.07
     commuting
    -0.06
     Mortgage
    -0.06
     wallet
    -0.06
    649
    -0.06
     sewage
    -0.06
     signal
    -0.05
     worsh
    -0.05
    POSITIVE LOGITS
     storage
    0.12
     Distribution
    0.11
    storage
    0.11
     distribution
    0.11
     deliveries
    0.10
     delivery
    0.10
    Distribution
    0.10
     warehouse
    0.10
     Storage
    0.10
     stor
    0.10
    Activations Density 0.077%

    No Known Activations