© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118378
    Prev
    Next
    INDEX
    Explanations

    references to the Kuramoto model and its variations

    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
    ÅĤaw
    -0.08
    iros
    -0.08
    nim
    -0.07
    nia
    -0.07
    ers
    -0.07
    esc
    -0.07
     mech
    -0.07
    eced
    -0.07
    ized
    -0.07
    ropic
    -0.07
    POSITIVE LOGITS
    iosity
    0.07
    dling
    0.06
     Absolute
    0.06
     absolute
    0.06
    alytics
    0.06
     dikke
    0.06
     DISCLAIM
    0.06
    riculum
    0.06
    ãĥĥãĥĹ
    0.06
    Absolute
    0.06
    Activations Density 0.013%

    No Known Activations