© 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. 17-LLAMASCOPE-RES-131K
    11. 29187
    Prev
    Next
    INDEX
    Explanations

    key terms related to various industries and sectors, especially in relation to economic activity and creativity

    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
    lya
    -0.08
     multin
    -0.07
    eldon
    -0.06
    sled
    -0.06
    _DEFINE
    -0.06
     Fro
    -0.06
    itch
    -0.06
     Ale
    -0.06
    tern
    -0.06
    /Main
    -0.06
    POSITIVE LOGITS
     industry
    0.10
     realm
    0.09
     field
    0.09
    isphere
    0.08
     world
    0.07
     community
    0.07
     sphere
    0.07
     category
    0.07
    industry
    0.07
     market
    0.07
    Activations Density 0.030%

    No Known Activations