© 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 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. 87915
    Prev
    Next
    INDEX
    Explanations

    technical programming terms and specific syntax elements

    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
     flush
    -0.06
     com
    -0.06
    -0.06
     %
    -0.06
     Stock
    -0.05
    à¹īà¸Ļà¸Ĺ
    -0.05
    ellido
    -0.05
    714
    -0.05
     uncon
    -0.05
     business
    -0.05
    POSITIVE LOGITS
    zyst
    0.08
    cea
    0.08
    afia
    0.08
    ucha
    0.08
    èŃľ
    0.08
    REFIX
    0.08
    parator
    0.07
     VÅ¡ech
    0.07
    _lua
    0.07
    leanup
    0.07
    Activations Density 0.001%

    No Known Activations