© 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. 16515
    Prev
    Next
    INDEX
    Explanations

    references to motorcycles and related activities

    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
    öy
    -0.07
    ê¶ģ
    -0.07
    reuse
    -0.07
    ype
    -0.07
    utilus
    -0.06
     swimming
    -0.06
     Rodgers
    -0.06
     programmes
    -0.06
    util
    -0.06
    миÑĢ
    -0.06
    POSITIVE LOGITS
     Motorcycle
    0.10
     motorcycle
    0.10
     helmet
    0.09
     Road
    0.09
     Ride
    0.09
     helmets
    0.09
    -road
    0.09
     riding
    0.09
     motorcycles
    0.08
     road
    0.08
    Activations Density 0.016%

    No Known Activations