© 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. 73994
    Prev
    Next
    INDEX
    Explanations

    references to Microsoft security updates and patches

    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
    Ùĩر
    -0.07
     McD
    -0.07
    phia
    -0.07
    /Peak
    -0.06
    VERRIDE
    -0.06
     PMID
    -0.06
    IXEL
    -0.06
    ãĤ¿ãĥ«
    -0.06
    @Spring
    -0.06
    ãĥĥãĤ¯
    -0.06
    POSITIVE LOGITS
     release
    0.08
     releases
    0.08
     released
    0.07
     advisory
    0.07
     Release
    0.07
     bulletin
    0.07
    esta
    0.07
     RELEASE
    0.07
    security
    0.07
     security
    0.06
    Activations Density 0.007%

    No Known Activations