© 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. 130329
    Prev
    Next
    INDEX
    Explanations

    topics related to government policies and military operations

    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
     wiÄĻc
    -0.07
    metic
    -0.07
    ãģĿãģĹãģ¦
    -0.07
     Canter
    -0.07
    ãĥ¼ãĥį
    -0.07
    ãģĹãĤĩ
    -0.07
     íijľìĭľ
    -0.06
    remen
    -0.06
    Ñıв
    -0.06
    oday
    -0.06
    POSITIVE LOGITS
     next
    0.09
     either
    0.09
     possibly
    0.09
     instead
    0.09
     if
    0.09
     would
    0.09
     possible
    0.09
     possibility
    0.09
     might
    0.08
    would
    0.08
    Activations Density 0.056%

    No Known Activations