© 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. 84335
    Prev
    Next
    INDEX
    Explanations

    references to economic and political sanctions

    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
    igest
    -0.06
     충
    -0.06
     Hive
    -0.06
    isor
    -0.06
     kaz
    -0.06
     Amazon
    -0.06
    Chars
    -0.06
    iper
    -0.05
    shaw
    -0.05
     leng
    -0.05
    POSITIVE LOGITS
    ÏĦεÏģ
    0.07
     Quincy
    0.07
    andel
    0.07
     Holy
    0.06
     Restricted
    0.06
     Cuban
    0.06
     Cuba
    0.06
    opa
    0.06
     restricted
    0.06
    aley
    0.06
    Activations Density 0.042%

    No Known Activations