© 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. 71275
    Prev
    Next
    INDEX
    Explanations

    phrases related to sponsorship and event presentation

    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
     FDA
    -0.07
    oucher
    -0.06
    egis
    -0.06
    alaria
    -0.06
    apon
    -0.06
     oa
    -0.06
    enville
    -0.06
    ÙģاÙĤ
    -0.06
    elman
    -0.06
    ç´°
    -0.06
    POSITIVE LOGITS
     sponsors
    0.10
     sponsor
    0.10
     sponsored
    0.09
    sponsor
    0.08
     Sponsored
    0.08
     insurer
    0.08
    -sponsored
    0.08
    ä½³
    0.08
     insurance
    0.07
     sponsorship
    0.07
    Activations Density 0.034%

    No Known Activations