© 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. 86491
    Prev
    Next
    INDEX
    Explanations

    names of people associated with politics and governance in Cuba

    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
    aque
    -0.07
    sus
    -0.06
    ione
    -0.06
     NSK
    -0.06
     dau
    -0.06
    æĹıèĩªæ²»
    -0.06
    ulet
    -0.06
    ing
    -0.06
    intr
    -0.06
    list
    -0.06
    POSITIVE LOGITS
     Labrador
    0.07
    UTTON
    0.07
     y
    0.07
    LLU
    0.06
    ÙĪØ«
    0.06
     Aval
    0.06
     Od
    0.06
     ÙħÙĤدÙħ
    0.06
    ÂŃs
    0.06
    ompiler
    0.06
    Activations Density 0.045%

    No Known Activations