© 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. 5028
    Prev
    Next
    INDEX
    Explanations

    references to economic sanctions and geopolitical issues

    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
    ochen
    -0.07
    invert
    -0.06
     clim
    -0.06
    itore
    -0.06
    SCRI
    -0.06
    inen
    -0.06
    è°ĥ
    -0.06
    icho
    -0.06
    ara
    -0.06
    atcher
    -0.06
    POSITIVE LOGITS
     laundering
    0.10
     freezing
    0.09
     launder
    0.08
     sanctions
    0.08
    AML
    0.08
     Anti
    0.08
     Wire
    0.07
     frozen
    0.07
     Hydra
    0.07
     freezes
    0.07
    Activations Density 0.112%

    No Known Activations