© 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. 15-LLAMASCOPE-RES-131K
    11. 103589
    Prev
    Next
    INDEX
    Explanations

    Words related to time references, specifically those indicating prior 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
    ằng
    -0.08
    /stats
    -0.08
     Kirby
    -0.07
    éļİ
    -0.07
    niž
    -0.07
     Courtney
    -0.07
    .between
    -0.07
    bdb
    -0.07
     Severity
    -0.06
    боÑĤ
    -0.06
    POSITIVE LOGITS
     Shaft
    0.07
    sha
    0.06
    .jsoup
    0.06
    shaft
    0.06
    otto
    0.06
    份
    0.06
    ipc
    0.06
     grace
    0.06
    LastError
    0.06
     ago
    0.06
    Activations Density 0.009%

    No Known Activations