© 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 EvalsExportsinterp-engineNEWAPI 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. 27459
    Prev
    Next
    INDEX
    Explanations

    terms related to conservation laws in theoretical physics

    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
    uka
    -0.08
    ityEngine
    -0.07
    voke
    -0.07
     Dome
    -0.07
    sigmoid
    -0.06
     srd
    -0.06
    spÄĽ
    -0.06
    phony
    -0.06
     Å¡ÃŃ
    -0.06
    vet
    -0.06
    POSITIVE LOGITS
     net
    0.11
     balanced
    0.10
     balances
    0.10
     Balance
    0.09
     conservation
    0.09
    balances
    0.09
     balance
    0.09
     Net
    0.09
     balancing
    0.09
    Balance
    0.08
    Activations Density 0.132%

    No Known Activations