© 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. 129543
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and equations related to synchronization in networks

    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
    Ïĥο
    -0.06
     elemental
    -0.06
     distortion
    -0.06
     formula
    -0.06
    립
    -0.06
     ãĤ¬
    -0.06
     RAW
    -0.05
     improv
    -0.05
     Shotgun
    -0.05
    oplan
    -0.05
    POSITIVE LOGITS
     Chaos
    0.09
    eniable
    0.08
    _Osc
    0.08
    /goto
    0.08
     attract
    0.07
    ollower
    0.07
    okane
    0.07
    offee
    0.07
     basin
    0.07
    /*č↵
    0.07
    Activations Density 0.119%

    No Known Activations