© 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. 40882
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and statistics related to sports or competitive events

    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
    usercontent
    -0.07
    olarity
    -0.07
    itchen
    -0.07
    ipo
    -0.07
    lessness
    -0.07
     Zah
    -0.07
    uckles
    -0.06
    sik
    -0.06
    ailure
    -0.06
    ová
    -0.06
    POSITIVE LOGITS
    ora
    0.07
    ãĥ
    0.07
     two
    0.06
    asse
    0.06
    ä¸įåı¯
    0.06
     double
    0.06
    adan
    0.06
     Bene
    0.06
    oras
    0.06
    Ñĩе
    0.06
    Activations Density 0.004%

    No Known Activations