© 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. 70172
    Prev
    Next
    INDEX
    Explanations

    technical programming elements related to configuration and system properties

    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
     proport
    -0.07
    athy
    -0.07
    /rss
    -0.07
    æ¡
    -0.07
    oola
    -0.07
    ãĤ¹ãĤ«
    -0.07
     SCN
    -0.06
    podob
    -0.06
    ASON
    -0.06
     suce
    -0.06
    POSITIVE LOGITS
    optera
    0.06
     --
    0.06
     -
    0.06
     sÆ°
    0.06
    .multipart
    0.06
    :selected
    0.06
     \↵
    0.06
    iÃŁ
    0.06
    adesh
    0.06
    ilha
    0.06
    Activations Density 0.006%

    No Known Activations