© 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 EvalsExportsAPI 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. 89006
    Prev
    Next
    INDEX
    Explanations

    themes related to community engagement and health awareness

    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
     Lange
    -0.07
    /misc
    -0.06
    akov
    -0.06
    ILA
    -0.06
     ça
    -0.06
     Lowe
    -0.05
    Charset
    -0.05
    iu
    -0.05
     tid
    -0.05
     Variant
    -0.05
    POSITIVE LOGITS
     myself
    0.08
     Wich
    0.08
     my
    0.08
     Ãľl
    0.07
    imson
    0.07
    pg
    0.07
    æĪijçļĦ
    0.07
     Wass
    0.07
    EndInit
    0.07
    iyorum
    0.07
    Activations Density 0.001%

    No Known Activations