© 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. 3671
    Prev
    Next
    INDEX
    Explanations

    resources and organizations related to social issues and assistance programs

    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
    áv
    -0.08
    .checkBox
    -0.06
    DOWNLOAD
    -0.06
    erne
    -0.06
     lo
    -0.06
     caption
    -0.06
     bin
    -0.06
    ãģ®ãģłãĤįãģĨ
    -0.06
     ho
    -0.06
    ê´
    -0.06
    POSITIVE LOGITS
     official
    0.11
    official
    0.08
     oficial
    0.08
     اÙĦÙħÙĪÙĤع
    0.07
     website
    0.07
    ckt
    0.07
     ìĽ¹ìĤ¬ìĿ´íĬ¸
    0.07
     Official
    0.07
    site
    0.07
     ffm
    0.07
    Activations Density 0.024%

    No Known Activations