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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 106371
    Prev
    Next
    INDEX
    Explanations

    terms related to political actions and decisions

    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
    uyo
    -0.07
     almost
    -0.07
     Canter
    -0.07
    Almost
    -0.07
    请éĢīæĭ©
    -0.06
    vette
    -0.06
     Almost
    -0.06
    almost
    -0.06
     ê±°ìĿĺ
    -0.06
    woke
    -0.06
    POSITIVE LOGITS
     or
    0.10
     somehow
    0.09
     either
    0.09
    -нибÑĥдÑĮ
    0.08
     oder
    0.08
    ëĿ¼ëıĦ
    0.07
     или
    0.07
     або
    0.07
     irgend
    0.07
     would
    0.07
    Activations Density 0.087%

    No Known Activations