© 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. 17-LLAMASCOPE-RES-131K
    11. 56096
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology's influence on work and business

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

    Headlines or article titles that appear at the beginning of blog posts or articles, often followed by publication dates, author information, or descriptive content.

    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
    eniable
    -0.07
     addCriterion
    -0.06
    ظ
    -0.06
    hana
    -0.06
    EMY
    -0.06
    sie
    -0.06
    ltre
    -0.06
    оÑīи
    -0.06
    inqu
    -0.06
    ibern
    -0.06
    POSITIVE LOGITS
     sometimes
    0.08
     many
    0.07
     Many
    0.07
     Sometimes
    0.06
    elo
    0.06
    Many
    0.06
     often
    0.06
    engl
    0.06
    ela
    0.06
    sometimes
    0.06
    Activations Density 0.022%

    No Known Activations