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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126465
    Prev
    Next
    INDEX
    Explanations

    mentions of "NHL" and related hockey terminology

    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
    tÃŃ
    -0.08
    immel
    -0.08
    ernote
    -0.08
    ingle
    -0.07
    ungle
    -0.07
     backpage
    -0.07
    ühr
    -0.07
    ÙĬات
    -0.07
     nét
    -0.07
    ataka
    -0.07
    POSITIVE LOGITS
     Western
    0.06
    374
    0.06
     Em
    0.06
    its
    0.06
    Ĥ
    0.06
    go
    0.06
    f
    0.06
    ittle
    0.05
    ITS
    0.05
     prim
    0.05
    Activations Density 0.001%

    No Known Activations