© 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. 118737
    Prev
    Next
    INDEX
    Explanations

    references to classic and historical cars, specifically their features and competitive history

    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
     software
    -0.06
     Patriot
    -0.06
    software
    -0.05
    oq
    -0.05
    own
    -0.05
    Reload
    -0.05
    ADDE
    -0.05
    uo
    -0.05
    TargetException
    -0.05
    ç§Ģ
    -0.05
    POSITIVE LOGITS
     putas
    0.08
    ï¼ĪæĺŃåĴĮ
    0.08
    ÛĮست
    0.07
    perimental
    0.07
    .EventHandler
    0.07
    .Match
    0.07
     Restoration
    0.07
    ÑģÑİ
    0.07
     Bubble
    0.07
    .googlecode
    0.06
    Activations Density 0.035%

    No Known Activations