© 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. 123889
    Prev
    Next
    INDEX
    Explanations

    references to electric mobility scooters and their features

    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
    graf
    -0.08
    .sys
    -0.07
    pheric
    -0.07
    ãĥĥãĥģ
    -0.06
    .Raw
    -0.06
    feeding
    -0.06
    oen
    -0.06
    æ¹
    -0.06
    /feed
    -0.06
    Ú¯Ùĩ
    -0.06
    POSITIVE LOGITS
     battery
    0.09
     Battery
    0.08
     recharge
    0.08
     walker
    0.08
     mobility
    0.07
     whe
    0.07
     wheel
    0.07
     electric
    0.07
     mop
    0.07
     Wheel
    0.07
    Activations Density 0.034%

    No Known Activations