© 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. 30452
    Prev
    Next
    INDEX
    Explanations

    references to horsepower and power specifications in automotive contexts

    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
    luž
    -0.09
    uler
    -0.08
    illard
    -0.08
    #echo
    -0.08
    dued
    -0.08
    ĨĴ
    -0.07
    raç
    -0.07
    ssel
    -0.07
    opensource
    -0.07
    /operators
    -0.07
    POSITIVE LOGITS
     outputs
    0.06
     rend
    0.06
     reserves
    0.06
     Gust
    0.05
    fulness
    0.05
     output
    0.05
     Gut
    0.05
    burst
    0.05
     peak
    0.05
    atts
    0.05
    Activations Density 0.003%

    No Known Activations