© 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. 16100
    Prev
    Next
    INDEX
    Explanations

    significant historical events and their impacts

    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
     recent
    -0.07
    orque
    -0.07
    мага
    -0.07
     Recent
    -0.07
    æ®
    -0.07
     lately
    -0.07
    tg
    -0.06
    recent
    -0.06
     ?><?
    -0.06
    urum
    -0.06
    POSITIVE LOGITS
     history
    0.09
    -history
    0.08
    æļ
    0.07
    history
    0.07
     History
    0.07
     HISTORY
    0.07
     jamais
    0.07
    History
    0.06
     world
    0.06
     worldwide
    0.06
    Activations Density 0.028%

    No Known Activations