© 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. 78515
    Prev
    Next
    INDEX
    Explanations

    financial metrics related to discounts and purchases

    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
    ůl
    -0.07
    AspectRatio
    -0.06
    corn
    -0.06
     Ñĥз
    -0.06
    stell
    -0.06
    ulses
    -0.06
     Ezra
    -0.06
    ulse
    -0.06
     elev
    -0.06
    idir
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĥ«ãĥī
    0.07
    924
    0.07
    ä¼ģ
    0.07
    ãĥ¼ãĥį
    0.06
     ARTICLE
    0.06
    anes
    0.06
    ledge
    0.06
    .schedulers
    0.06
     Flames
    0.06
    ä¹ĭ
    0.06
    Activations Density 0.004%

    No Known Activations