© 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. 61042
    Prev
    Next
    INDEX
    Explanations

    important concepts related to health and well-being

    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
     Fe
    -0.06
    ycl
    -0.06
     blank
    -0.06
    este
    -0.06
    -0.06
     i
    -0.06
    ivo
    -0.06
     in
    -0.06
    ing
    -0.05
     int
    -0.05
    POSITIVE LOGITS
     että
    0.09
     rằng
    0.08
     bahwa
    0.08
    edException
    0.07
    .Companion
    0.07
    ìķł
    0.07
     âĹĦ
    0.07
    vap
    0.07
    人ãģĮ
    0.07
    .xhtml
    0.07
    Activations Density 0.042%

    No Known Activations