© 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. 18234
    Prev
    Next
    INDEX
    Explanations

    discussions related to U.S. foreign intervention policies and political opinions on conflicts

    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
    aight
    -0.07
    eworld
    -0.07
    argas
    -0.07
    amespace
    -0.06
    inder
    -0.06
    INGER
    -0.06
    gang
    -0.06
    klad
    -0.06
     Fairfield
    -0.06
    agma
    -0.06
    POSITIVE LOGITS
     ex
    0.07
     antic
    0.07
     TaÅŁ
    0.07
    Ø´ÙĨ
    0.07
     democracy
    0.07
     Democracy
    0.07
    Ïģίζ
    0.06
    ää
    0.06
    reb
    0.06
    ãĥ³ãĥģ
    0.06
    Activations Density 0.179%

    No Known Activations