© 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 EvalsExportsinterp-engineNEWAPI 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. 73545
    Prev
    Next
    INDEX
    Explanations

    mathematical elements related to graph theory and sets

    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
    367
    -0.06
    stanov
    -0.06
    znik
    -0.06
    RING
    -0.06
    690
    -0.06
    vtk
    -0.05
     sympt
    -0.05
    лож
    -0.05
    Ïĥο
    -0.05
    orsi
    -0.05
    POSITIVE LOGITS
    ulse
    0.07
    alm
    0.07
    ele
    0.07
    ood
    0.07
    ryfall
    0.06
     Ipsum
    0.06
    ryn
    0.06
    uden
    0.06
    ynes
    0.06
    oplevel
    0.06
    Activations Density 0.056%

    No Known Activations