© 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. 15341
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming constructs that indicate the creation of new objects or classes

    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
     Pike
    -0.07
    รม
    -0.06
    722
    -0.06
    387
    -0.06
    _finalize
    -0.06
    724
    -0.06
     Flake
    -0.06
    386
    -0.06
    723
    -0.05
    stvÃŃ
    -0.05
    POSITIVE LOGITS
    é¨
    0.07
    _dispatcher
    0.07
    ̧
    0.07
    ãĤ¹ãĤ«
    0.07
    è¨Ģãģ£ãģŁ
    0.07
    xima
    0.07
    ylvania
    0.06
    agn
    0.06
    ìķĻ
    0.06
     èĹ
    0.06
    Activations Density 0.014%

    No Known Activations