© 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. 82635
    Prev
    Next
    INDEX
    Explanations

    references to government actions and historical political events

    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
    rei
    -0.07
    ennon
    -0.07
    çķ
    -0.07
     conservatives
    -0.06
    nech
    -0.06
    eton
    -0.06
    γκα
    -0.06
    Migration
    -0.06
     Conservatives
    -0.06
     Migration
    -0.06
    POSITIVE LOGITS
     worker
    0.08
     Worker
    0.08
     redistrib
    0.08
     workers
    0.07
     redistribution
    0.07
    worker
    0.07
    ανά
    0.07
     Redistribution
    0.07
    -worker
    0.07
     Workers
    0.07
    Activations Density 0.055%

    No Known Activations