© 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. 39720
    Prev
    Next
    INDEX
    Explanations

    details related to racing events and qualifying sessions

    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
     Bilim
    -0.06
    istrovstvÃŃ
    -0.06
    ç´Ģ
    -0.06
     Rai
    -0.06
    anio
    -0.06
     birthdays
    -0.06
    oulos
    -0.06
     견
    -0.06
     vil
    -0.06
    asiswa
    -0.06
    POSITIVE LOGITS
    jak
    0.07
     Tomorrow
    0.07
     Bye
    0.07
     session
    0.07
    auty
    0.06
    OfDay
    0.06
    çݯ
    0.06
     Alo
    0.06
    ernen
    0.06
    igor
    0.06
    Activations Density 0.008%

    No Known Activations