© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74451
    Prev
    Next
    INDEX
    Explanations

    statistical achievements and performance metrics in sports

    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
    strand
    -0.06
    nen
    -0.06
     Hava
    -0.06
    vern
    -0.06
    YT
    -0.06
    oven
    -0.06
    bic
    -0.06
    ovo
    -0.06
     Hath
    -0.06
    erras
    -0.06
    POSITIVE LOGITS
    iyon
    0.08
     jÃŃ
    0.07
     overall
    0.07
     earned
    0.06
    ÙĪØ¯Ùĩ
    0.06
    Ø¢Ùħ
    0.06
    kola
    0.06
     кÑĢок
    0.06
    าม
    0.06
    aus
    0.06
    Activations Density 0.001%

    No Known Activations