© 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. 129267
    Prev
    Next
    INDEX
    Explanations

    various forms and techniques of welding processes

    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
     McInt
    -0.07
    oton
    -0.06
    chio
    -0.06
    ael
    -0.06
     storage
    -0.06
    allet
    -0.06
     Sle
    -0.06
    ocker
    -0.06
     Snyder
    -0.06
    awn
    -0.05
    POSITIVE LOGITS
    iterals
    0.08
    entifier
    0.08
    fahren
    0.08
    سط
    0.08
    BufferData
    0.07
    à¥Ŀ
    0.07
     ********************************************************
    0.07
    οÏħÏģγ
    0.07
    .ActionListener
    0.07
    suma
    0.07
    Activations Density 0.013%

    No Known Activations