© 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. 91923
    Prev
    Next
    INDEX
    Explanations

    mathematical statements about properties of graphs and their characteristics

    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
    .freeze
    -0.06
    IVA
    -0.06
     ÑıÑĢ
    -0.06
    vana
    -0.06
     TextAlign
    -0.06
    Gro
    -0.06
    ierre
    -0.06
    Configurer
    -0.06
    åIJİçļĦ
    -0.06
    ãĥ¼ãĤ¹
    -0.06
    POSITIVE LOGITS
    ark
    0.07
    arken
    0.07
     assum
    0.06
    573
    0.06
    ¤í
    0.06
    ervo
    0.06
     necessarily
    0.06
    ury
    0.06
    âĢĮاÙĨ
    0.06
    /is
    0.06
    Activations Density 0.076%

    No Known Activations