© 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. 15-LLAMASCOPE-RES-131K
    11. 87454
    Prev
    Next
    INDEX
    Explanations

    references to gymnastics and related competitive events

    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
     sed
    -0.07
     Sed
    -0.07
    argout
    -0.07
    ê¼
    -0.07
    _finalize
    -0.07
    лага
    -0.06
     dra
    -0.06
    ãģĭãģij
    -0.06
    Uvs
    -0.06
     Madden
    -0.06
    POSITIVE LOGITS
    iew
    0.08
     prec
    0.07
     Vaults
    0.06
     gymn
    0.06
     mains
    0.06
    iros
    0.06
    dq
    0.06
    landing
    0.06
     плаÑģÑĤи
    0.06
     posting
    0.06
    Activations Density 0.003%

    No Known Activations