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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 81866
    Prev
    Next
    INDEX
    Explanations

    instances of competitive sports events and related controversies

    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
    orthand
    -0.07
     Garten
    -0.06
    Weak
    -0.06
    okus
    -0.06
    ouce
    -0.06
    uten
    -0.06
    illard
    -0.06
    ammer
    -0.06
    iny
    -0.06
    opp
    -0.06
    POSITIVE LOGITS
     tensions
    0.07
     temper
    0.07
     heated
    0.07
     Temper
    0.07
    ensions
    0.07
     peace
    0.06
    /tos
    0.06
     pac
    0.06
     temp
    0.06
    à¹Ģà¸Ł
    0.06
    Activations Density 0.018%

    No Known Activations