© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 84873
    Prev
    Next
    INDEX
    Explanations

    lines of code involving serial communication and error handling in programming

    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
    achten
    -0.07
    623
    -0.07
    agnar
    -0.07
     Elk
    -0.06
    pent
    -0.06
     ****************************************************************************
    -0.06
    706
    -0.06
    rana
    -0.06
    OrCreate
    -0.06
    overe
    -0.06
    POSITIVE LOGITS
     Fare
    0.07
    erah
    0.06
    	defer
    0.06
     followed
    0.06
    ero
    0.06
    æľ«
    0.06
     ham
    0.06
     sign
    0.06
     defer
    0.06
     Hiç
    0.06
    Activations Density 0.078%

    No Known Activations