© 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. 15-LLAMASCOPE-RES-131K
    11. 27499
    Prev
    Next
    INDEX
    Explanations

    information related to sports eligibility and scoring criteria

    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
     Cousins
    -0.08
    wal
    -0.07
    >{!!
    -0.06
     maybe
    -0.05
    Missing
    -0.05
    ic
    -0.05
    éļı
    -0.05
     Missing
    -0.05
     Miller
    -0.05
    jom
    -0.05
    POSITIVE LOGITS
     khúc
    0.07
    .Bind
    0.07
    emouth
    0.07
    HORT
    0.07
     addCriterion
    0.07
     çĬ
    0.07
    addock
    0.06
     embr
    0.06
    æłªå¼ıä¼ļ社
    0.06
     èIJ
    0.06
    Activations Density 0.011%

    No Known Activations