© 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 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. 16521
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to graph theory and properties of graphs

    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
    ANDROID
    -0.06
     Cuomo
    -0.06
     Cart
    -0.06
     Getty
    -0.06
    /thumb
    -0.06
    ilim
    -0.06
     gener
    -0.06
    interop
    -0.06
    ppe
    -0.06
     Carlton
    -0.05
    POSITIVE LOGITS
     graph
    0.08
     Maj
    0.07
    ovit
    0.07
    PropertyValue
    0.07
     Floyd
    0.07
    ÑģÑĤÑİ
    0.06
    787
    0.06
    alon
    0.06
    æŁĵ
    0.06
    Å¡ov
    0.06
    Activations Density 0.326%

    No Known Activations