© 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. 119208
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to particle collisions in physics experiments

    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
    ernels
    -0.06
    CCCCCC
    -0.06
     piece
    -0.06
     retard
    -0.06
    GetInstance
    -0.06
    ysz
    -0.06
     Chr
    -0.06
     mark
    -0.05
    uppy
    -0.05
    upp
    -0.05
    POSITIVE LOGITS
    orthand
    0.07
    ardin
    0.07
    furt
    0.06
     lá»ħ
    0.06
     Bram
    0.06
     collisions
    0.06
    alice
    0.06
    itchen
    0.06
    TeV
    0.06
     tÃŃn
    0.06
    Activations Density 0.024%

    No Known Activations