© 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. 30999
    Prev
    Next
    INDEX
    Explanations

    terms related to object instantiation and properties 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
    erdem
    -0.07
    ehler
    -0.07
    weis
    -0.06
    ogui
    -0.06
    phinx
    -0.06
    ucha
    -0.06
    pies
    -0.06
     Buch
    -0.06
    rgan
    -0.06
     Chu
    -0.06
    POSITIVE LOGITS
    ital
    0.07
    baby
    0.07
    uns
    0.07
    缮ãģ®
    0.07
    ToBounds
    0.07
    ıt
    0.07
    Baby
    0.07
    kok
    0.06
    apr
    0.06
     uns
    0.06
    Activations Density 0.001%

    No Known Activations