© 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. 126548
    Prev
    Next
    INDEX
    Explanations

    phrases related to contest winners and lottery prizes

    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
    iga
    -0.06
    าà¸ĩ
    -0.06
    =search
    -0.06
    STA
    -0.06
    paralle
    -0.06
    zial
    -0.06
    onio
    -0.06
     à¤Ĺत
    -0.06
    zin
    -0.06
    èİİ
    -0.06
    POSITIVE LOGITS
     prize
    0.09
    agues
    0.07
    asc
    0.07
    ogue
    0.07
     Prize
    0.07
     prizes
    0.07
     winners
    0.06
    accept
    0.06
     acceptance
    0.06
    ove
    0.06
    Activations Density 0.002%

    No Known Activations