© 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. 127267
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terminology related to graph theory

    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
    indow
    -0.07
    agli
    -0.07
    issy
    -0.07
    <translation
    -0.07
    uko
    -0.07
    wash
    -0.07
    iele
    -0.07
    inke
    -0.07
    ubern
    -0.07
    ihan
    -0.07
    POSITIVE LOGITS
     TMPro
    0.06
    sett
    0.06
    =lambda
    0.06
    ³
    0.06
    :not
    0.06
    Kn
    0.05
     .=
    0.05
    zm
    0.05
     jun
    0.05
     traces
    0.05
    Activations Density 0.027%

    No Known Activations