© 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. 29453
    Prev
    Next
    INDEX
    Explanations

    specific tools and equipment related to mechanical tasks

    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
    rell
    -0.07
    bote
    -0.07
    hlen
    -0.07
    culo
    -0.07
    udev
    -0.07
    bullet
    -0.07
    wash
    -0.07
    麦
    -0.07
    coop
    -0.07
    iculos
    -0.07
    POSITIVE LOGITS
     tool
    0.14
     Tool
    0.12
     tools
    0.11
    å·¥åħ·
    0.10
    tool
    0.10
    Tool
    0.10
    -tool
    0.09
     TOOL
    0.09
     rescue
    0.08
    (tool
    0.08
    Activations Density 0.050%

    No Known Activations