© 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. 72426
    Prev
    Next
    INDEX
    Explanations

    terms and discussions related to dark photon constraints and implications 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
    ÙĪص
    -0.07
    utzer
    -0.06
    ULA
    -0.06
    agascar
    -0.06
    oce
    -0.06
    addle
    -0.06
    è¨Ī
    -0.06
     filmer
    -0.06
    ypo
    -0.06
    íĥĢìĿ´
    -0.06
    POSITIVE LOGITS
     ranges
    0.07
     Wyn
    0.07
    obia
    0.06
     Upper
    0.06
     limits
    0.06
     synthes
    0.06
    æIJľ
    0.06
     range
    0.06
     bounds
    0.06
     constraints
    0.06
    Activations Density 0.070%

    No Known Activations