© 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 EvalsExportsinterp-engineNEWAPI 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. 58331
    Prev
    Next
    INDEX
    Explanations

    monetary values and discounts related to shopping and employee payments

    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
    -0.07
    Cog
    -0.07
    uish
    -0.06
     setting
    -0.06
     alone
    -0.06
     arch
    -0.06
     PC
    -0.06
     version
    -0.05
     pc
    -0.05
    íĹĮ
    -0.05
    POSITIVE LOGITS
    /order
    0.08
     maduras
    0.08
    ë¶Ī
    0.07
    ias
    0.07
    affen
    0.07
    Interop
    0.07
    ftime
    0.07
    illery
    0.07
    NetMessage
    0.07
    iller
    0.07
    Activations Density 0.003%

    No Known Activations