© 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. 15-LLAMASCOPE-RES-131K
    11. 89315
    Prev
    Next
    INDEX
    Explanations

    code structure and elements related to interfaces and object-oriented programming design patterns

    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
    ilog
    -0.07
    hana
    -0.07
     componentName
    -0.07
    etten
    -0.06
    ooth
    -0.06
    erties
    -0.06
    oui
    -0.06
    edd
    -0.06
    imli
    -0.06
    rega
    -0.06
    POSITIVE LOGITS
     crush
    0.07
     punch
    0.06
    rieve
    0.06
    ource
    0.06
     Crush
    0.06
    CHANT
    0.06
    ropoda
    0.06
    æ¨Ļ
    0.06
    reau
    0.06
     Shoes
    0.06
    Activations Density 0.063%

    No Known Activations