© 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. 56478
    Prev
    Next
    INDEX
    Explanations

    references to time travel and its implications

    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
    entes
    -0.07
    mers
    -0.07
    ãĤĮãģ©
    -0.07
    _ghost
    -0.07
    azen
    -0.07
    ãĥ¡ãĥ©
    -0.07
    itsu
    -0.07
    arella
    -0.06
     crem
    -0.06
     consect
    -0.06
    POSITIVE LOGITS
     events
    0.08
     future
    0.07
    oy
    0.07
     history
    0.06
     Events
    0.06
     world
    0.06
     altered
    0.06
    æľªæĿ¥
    0.06
     Alt
    0.06
     everything
    0.06
    Activations Density 0.016%

    No Known Activations