© 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. 60887
    Prev
    Next
    INDEX
    Explanations

    various types of flooring services and installations

    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
     Bund
    -0.07
    ساÙĨ
    -0.07
    uggle
    -0.07
    CTest
    -0.07
    agraph
    -0.06
    -facebook
    -0.06
    âl
    -0.06
    ç·´
    -0.06
    Craft
    -0.06
    irq
    -0.06
    POSITIVE LOGITS
    504
    0.07
    omu
    0.07
    Prim
    0.06
     Morr
    0.06
     prim
    0.06
     such
    0.06
     Zucker
    0.06
     discret
    0.06
    /fixtures
    0.06
     requ
    0.06
    Activations Density 0.010%

    No Known Activations