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

    Neuronpedia

    Jacobian LensNEW
    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. 88731
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific references and citations

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

    Punctuation and formatting elements at section boundaries in academic or scientific documents, often appearing before section headings or at the end of paragraphs preceding new 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
    velle
    -0.07
    allest
    -0.06
     McGregor
    -0.06
    olle
    -0.06
    indle
    -0.06
     zone
    -0.06
    lius
    -0.06
    lava
    -0.06
     formulas
    -0.06
    isters
    -0.06
    POSITIVE LOGITS
     xOffset
    0.07
    åIJ¹
    0.07
    å¨ĺ
    0.07
    ÑĪиб
    0.07
    ãĥ¼ãĥĸ
    0.06
    Aspect
    0.06
    ÌĨ
    0.06
    _PRED
    0.06
    ÑĢави
    0.06
    æı
    0.06
    Activations Density 0.009%

    No Known Activations