© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 60451
    Prev
    Next
    INDEX
    Explanations

    mentions of countries, their leaders, and geopolitical entities

    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
     assistants
    -0.08
    ̣
    -0.07
    ariate
    -0.07
     Garr
    -0.06
    [sub
    -0.06
    elper
    -0.06
    ensis
    -0.06
    æĮ¯ãĤĬ
    -0.06
    usercontent
    -0.06
    âĹĭ
    -0.06
    POSITIVE LOGITS
     leader
    0.13
     president
    0.10
     President
    0.10
     founder
    0.10
     chief
    0.10
     boss
    0.09
    leader
    0.09
     head
    0.09
     Chief
    0.08
     leaders
    0.08
    Activations Density 0.028%

    No Known Activations