© 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. 106303
    Prev
    Next
    INDEX
    Explanations

    technical instructions related to coding or programming

    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
    侧
    -0.08
    lemn
    -0.07
    olon
    -0.07
    rawer
    -0.07
    URRED
    -0.07
    .scalablytyped
    -0.07
    allon
    -0.07
    WindowTitle
    -0.06
    treeview
    -0.06
    -dismissible
    -0.06
    POSITIVE LOGITS
    ŀæĢ§
    0.08
    916
    0.06
     Thi
    0.06
    970
    0.06
     CSS
    0.06
    100
    0.06
     DÃŃky
    0.06
     float
    0.06
     Anch
    0.06
     solid
    0.06
    Activations Density 0.017%

    No Known Activations