© 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. 30866
    Prev
    Next
    INDEX
    Explanations

    references to Olympic sports and competitions

    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
    -0.07
     £
    -0.07
    iasi
    -0.06
    	throws
    -0.06
    NOP
    -0.06
     fucking
    -0.06
     Uk
    -0.06
    anzeigen
    -0.06
    ekil
    -0.06
     gad
    -0.06
    POSITIVE LOGITS
    aks
    0.07
    avers
    0.07
    bron
    0.06
    :checked
    0.06
    éĥİ
    0.06
    ithe
    0.06
     Lak
    0.06
     quot
    0.06
    yc
    0.06
    hon
    0.06
    Activations Density 0.013%

    No Known Activations