© 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. 39767
    Prev
    Next
    INDEX
    Explanations

    references to injuries and their impact on player performance

    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
     helf
    -0.08
    ninger
    -0.07
    ÏĦοι
    -0.07
    анов
    -0.06
    Indented
    -0.06
    ι
    -0.06
    νÏī
    -0.06
    νÏĮ
    -0.06
    Argb
    -0.06
    entai
    -0.06
    POSITIVE LOGITS
     worst
    0.07
     radi
    0.06
    oria
    0.06
     seriousness
    0.06
    riage
    0.06
     nature
    0.06
    anj
    0.06
    radi
    0.06
     tonight
    0.06
     Serv
    0.06
    Activations Density 0.007%

    No Known Activations