© 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. 88979
    Prev
    Next
    INDEX
    Explanations

    references to free educational resources and structured content

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

    Fragments of text typically appearing in web scraping results, including partial words from product descriptions, code snippets, and website elements.

    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
    icons
    -0.07
    egis
    -0.06
    ephir
    -0.06
    isman
    -0.06
    alchemy
    -0.06
    lava
    -0.06
    æ²¢
    -0.06
    amet
    -0.06
    agree
    -0.06
    .removeEventListener
    -0.06
    POSITIVE LOGITS
    usercontent
    0.09
    -transitional
    0.07
    Jvm
    0.06
    162
    0.06
     com
    0.06
     sÃłng
    0.06
    eus
    0.06
    Deprecated
    0.06
    PEND
    0.06
    esh
    0.06
    Activations Density 0.004%

    No Known Activations