© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 17080
    Prev
    Next
    INDEX
    Explanations

    phrases related to synchronization and coordination in systems

    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
    marsh
    -0.07
    ughter
    -0.07
    emie
    -0.07
    lg
    -0.07
    ISCO
    -0.06
    weg
    -0.06
    à¹Ĥล
    -0.06
    icina
    -0.06
    onde
    -0.06
    jos
    -0.06
    POSITIVE LOGITS
    ron
    0.10
    ingly
    0.08
    posium
    0.08
    (sync
    0.08
    rh
    0.07
    istar
    0.07
    OPSIS
    0.07
    -minded
    0.07
    icut
    0.07
    s
    0.07
    Activations Density 0.010%

    No Known Activations