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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26467
    Prev
    Next
    INDEX
    Explanations

    references to acknowledgments and citations within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX document commands and environments typically used in academic papers, particularly for formatting elements like acknowledgments, tables, notes, citations, and special document sections.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ivas
    -0.08
    è¡Ľ
    -0.07
    omp
    -0.07
    Mahon
    -0.07
     Depot
    -0.07
     hva
    -0.07
    ãĤĤãģĨ
    -0.07
    audi
    -0.07
    adar
    -0.07
    agal
    -0.07
    POSITIVE LOGITS
    WithPath
    0.06
    ama
    0.06
     affili
    0.06
    599
    0.06
    Cerrar
    0.05
    iliation
    0.05
    AndView
    0.05
     $#
    0.05
    iverse
    0.05
    ÙĪÙĤع
    0.05
    Activations Density 0.010%

    No Known Activations