© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107234
    Prev
    Next
    INDEX
    Explanations

    sports-related terminology and 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
    istrovstvÃŃ
    -0.08
     Orr
    -0.07
    adiens
    -0.06
     ____
    -0.06
    UK
    -0.06
    ¼åIJĪ
    -0.06
     [~,
    -0.06
     Mehmet
    -0.06
    asic
    -0.06
    oubtedly
    -0.06
    POSITIVE LOGITS
    .ht
    0.06
    _ti
    0.06
    eldom
    0.06
    elsen
    0.06
    .manage
    0.06
    ANTE
    0.06
    į¼
    0.06
    ãĥªãĤ«
    0.06
    ONA
    0.06
     envis
    0.06
    Activations Density 0.014%

    No Known Activations