© 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. 117863
    Prev
    Next
    INDEX
    Explanations

    information related to software features and updates, particularly concerning SharePoint and Microsoft products

    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
    ONO
    -0.08
    надлеж
    -0.07
    ÌĤ
    -0.07
     ç¤
    -0.07
    æī£
    -0.07
    beit
    -0.07
     Gameplay
    -0.07
    CTOR
    -0.06
    stitutions
    -0.06
    ãĥ¶
    -0.06
    POSITIVE LOGITS
     support
    0.08
     product
    0.07
     Support
    0.07
    support
    0.07
     announcement
    0.07
     discontin
    0.06
     development
    0.06
     continued
    0.06
     announced
    0.06
     Unsupported
    0.06
    Activations Density 0.012%

    No Known Activations