© 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. 28425
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to market dynamics and established businesses

    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
    .scalablytyped
    -0.08
    .updateDynamic
    -0.07
    mlin
    -0.07
    hend
    -0.07
    oram
    -0.07
    regation
    -0.07
    raç
    -0.07
    hari
    -0.07
    rena
    -0.07
    /latest
    -0.07
    POSITIVE LOGITS
    :
    0.08
     ÙħØ«ÙĦا
    0.07
    :↵
    0.07
    çļĦæĺ¯
    0.07
    287
    0.06
     ÙģاÙĦ
    0.06
    åIJĦç§į
    0.06
    ohn
    0.06
    such
    0.06
     napÅĻ
    0.06
    Activations Density 0.024%

    No Known Activations