© 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. 85298
    Prev
    Next
    INDEX
    Explanations

    concepts and terminology related to advanced theoretical physics, particularly focusing on Hamiltonian and Lagrangian formulations

    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
    /tiny
    -0.07
    /misc
    -0.07
     question
    -0.06
     MLA
    -0.06
    ingly
    -0.06
     Question
    -0.06
    Äįas
    -0.06
    ìĭ±
    -0.05
    iness
    -0.05
     tack
    -0.05
    POSITIVE LOGITS
    addock
    0.07
    airo
    0.07
    SSERT
    0.07
    ãĥĥãĥī
    0.07
    utm
    0.07
    ToProps
    0.07
    heits
    0.07
    phies
    0.07
    irket
    0.07
    amespace
    0.07
    Activations Density 0.049%

    No Known Activations