© 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. 41088
    Prev
    Next
    INDEX
    Explanations

    statistical averages 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
    égor
    -0.06
     ump
    -0.06
    æķ£
    -0.06
    TIMER
    -0.06
    ystick
    -0.05
     Gaw
    -0.05
    endregion
    -0.05
    wal
    -0.05
     populous
    -0.05
    nr
    -0.05
    POSITIVE LOGITS
    InSeconds
    0.07
    gene
    0.06
    acular
    0.06
     Duck
    0.06
    imli
    0.06
    изнеÑģ
    0.06
    íıŃ
    0.06
    imal
    0.06
     Nut
    0.06
    åĪĩ
    0.06
    Activations Density 0.013%

    No Known Activations