© 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. 75077
    Prev
    Next
    INDEX
    Explanations

    references to UFC events and associated activities

    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
    Dual
    -0.08
     dual
    -0.07
    ÑĢеб
    -0.07
    ÌĨ
    -0.07
     tun
    -0.07
     Dual
    -0.07
    abis
    -0.06
    hiba
    -0.06
    suma
    -0.06
    reater
    -0.06
    POSITIVE LOGITS
     беÑĢ
    0.06
    amma
    0.06
    iot
    0.06
    primer
    0.06
    ibble
    0.06
    .uf
    0.06
     Barcl
    0.06
     Expr
    0.06
    iku
    0.06
     UFC
    0.05
    Activations Density 0.004%

    No Known Activations