© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 116641
    Prev
    Next
    INDEX
    Explanations

    references to various types of welding and material joining 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
    าะ
    -0.07
    лÑıн
    -0.07
    azen
    -0.07
    γοÏį
    -0.07
    ÄĽt
    -0.06
    _IDENT
    -0.06
    à¹īà¸Ńม
    -0.06
    chein
    -0.06
    bk
    -0.06
    ancia
    -0.06
    POSITIVE LOGITS
     joining
    0.13
     join
    0.12
    joining
    0.11
     bonds
    0.11
     bond
    0.11
     joins
    0.10
    join
    0.10
     Join
    0.10
     bonding
    0.10
     binding
    0.10
    Activations Density 0.130%

    No Known Activations