© 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. 41578
    Prev
    Next
    INDEX
    Explanations

    expressions of collaboration and initiative within community projects

    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
     dramatically
    -0.06
     jobject
    -0.06
    earn
    -0.06
    rat
    -0.06
     famously
    -0.05
    enkins
    -0.05
    etrain
    -0.05
     sophistication
    -0.05
     Counter
    -0.05
     rit
    -0.05
    POSITIVE LOGITS
     indeb
    0.07
    upy
    0.07
    ä¸Ģ人
    0.07
    ìĹħì²´
    0.07
    à¥Ģà¤ıम
    0.07
     ý
    0.06
     Byl
    0.06
    æ»
    0.06
     bureaucr
    0.06
    helm
    0.06
    Activations Density 0.003%

    No Known Activations