© 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. 94405
    Prev
    Next
    INDEX
    Explanations

    references to various currencies and their economic implications

    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
    cntl
    -0.07
    ed
    -0.07
    509
    -0.07
    ing
    -0.06
     san
    -0.06
    à¸Ļวà¸Ļ
    -0.06
    째
    -0.06
    orsk
    -0.06
     Gan
    -0.06
    fait
    -0.06
    POSITIVE LOGITS
    TestFixture
    0.08
     cins
    0.07
    assic
    0.07
    ERRU
    0.07
    /rand
    0.07
     karÄ±ÅŁ
    0.07
    OwnerId
    0.07
    ë¹Ľ
    0.07
    ColumnsMode
    0.07
     weakness
    0.06
    Activations Density 0.014%

    No Known Activations