© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 439
    Prev
    Next
    INDEX
    Explanations

    references to duality, contrast, or parallels in various contexts

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

    Opening or closing punctuation marks (especially parentheses) that introduce explanations, translations, or clarifications of preceding specialized terms, acronyms, or foreign words.

    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
    burgh
    -0.06
    Pocket
    -0.06
    ilent
    -0.06
    775
    -0.06
    ymph
    -0.06
     ãĢī
    -0.06
     kred
    -0.06
    aring
    -0.06
    okino
    -0.06
     pornos
    -0.06
    POSITIVE LOGITS
    valuator
    0.07
    uyo
    0.06
    ulu
    0.06
    ipse
    0.06
     rebut
    0.06
    ô
    0.06
    ään
    0.06
    -cols
    0.06
     Ru
    0.06
     mdi
    0.06
    Activations Density 0.051%

    No Known Activations