© 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. 27958
    Prev
    Next
    INDEX
    Explanations

    references to motorcycle racing and notable racers

    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
     ford
    -0.06
    TEL
    -0.06
     car
    -0.06
     Chevy
    -0.06
    ivan
    -0.05
     Soy
    -0.05
     probabil
    -0.05
    豪
    -0.05
     Malay
    -0.05
    utton
    -0.05
    POSITIVE LOGITS
    bike
    0.11
     bike
    0.10
     Motorcycle
    0.10
     bikes
    0.10
     motorcycle
    0.09
     Bike
    0.09
     rider
    0.09
     Rider
    0.09
     helmets
    0.09
     riders
    0.09
    Activations Density 0.059%

    No Known Activations