© 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 EvalsExportsinterp-engineNEWAPI 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. 1777
    Prev
    Next
    INDEX
    Explanations

    instances of transactional interactions and exchanges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    angler
    -0.08
    chema
    -0.06
    âĢ¦the
    -0.06
    رÙĬر
    -0.06
     wen
    -0.06
    cling
    -0.06
    alla
    -0.06
     butt
    -0.06
    amp
    -0.06
     abi
    -0.05
    POSITIVE LOGITS
    ï¼ĮçĦ¶åIJİ
    0.09
    çĦ¶åIJİ
    0.09
     nhÆ°ng
    0.09
     but
    0.09
    {{{
    0.08
    ATAB
    0.07
    then
    0.07
    acci
    0.07
     rá»ĵi
    0.07
     pero
    0.07
    Activations Density 0.054%

    No Known Activations