© 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. 88560
    Prev
    Next
    INDEX
    Explanations

    content related to academic achievements and opportunities

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

    Section headers or navigation elements on websites, often appearing in pairs that indicate content categories, links, or date ranges. These typically function as clickable elements in website menus, sidebars, or footers.

    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
     Slater
    -0.06
    hack
    -0.06
     sole
    -0.06
    íĥķ
    -0.06
    619
    -0.06
    ório
    -0.05
    629
    -0.05
    eward
    -0.05
    Hack
    -0.05
    riott
    -0.05
    POSITIVE LOGITS
     newest
    0.09
     update
    0.09
    æĸ°çļĦ
    0.08
     updates
    0.08
    ç»Īäºİ
    0.08
     news
    0.08
     announce
    0.08
    updates
    0.08
     new
    0.08
     announcement
    0.08
    Activations Density 0.148%

    No Known Activations