© 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. 42418
    Prev
    Next
    INDEX
    Explanations

    references to combining or managing different elements in a system

    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
    ÑĨÑİ
    -0.08
     Yue
    -0.06
     æ®
    -0.06
    à¸İ
    -0.06
     part
    -0.06
    rack
    -0.05
     Mayo
    -0.05
     Twig
    -0.05
     Tiny
    -0.05
    ãĥĥãĥģ
    -0.05
    POSITIVE LOGITS
     single
    0.18
    single
    0.16
    -single
    0.14
    /single
    0.14
     SINGLE
    0.14
    _single
    0.13
     Single
    0.13
    Single
    0.13
    (single
    0.12
     еди
    0.12
    Activations Density 0.061%

    No Known Activations