© 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. 28258
    Prev
    Next
    INDEX
    Explanations

    references to international treaties and their consequences

    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
    getter
    -0.07
    abela
    -0.07
    atabase
    -0.07
    /xhtml
    -0.07
    ÙĦÙħ
    -0.06
    æIJ
    -0.06
    ë§IJ
    -0.06
    æŃ¢
    -0.06
     autom
    -0.06
    poon
    -0.06
    POSITIVE LOGITS
    193
    0.07
    194
    0.07
    anim
    0.07
     humili
    0.06
    hawks
    0.06
     peace
    0.06
    191
    0.06
     Hitler
    0.06
     æĻ´
    0.06
    eel
    0.05
    Activations Density 0.112%

    No Known Activations