© 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. 9-LLAMASCOPE-RES-131K
    11. 95307
    Prev
    Next
    INDEX
    Explanations

    aspects of sports events related to tournament draws and qualifying rounds

    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
     Lorem
    -0.07
    igne
    -0.06
     æ¹
    -0.06
     hist
    -0.06
    ajas
    -0.06
    zug
    -0.06
    uzzi
    -0.06
    undra
    -0.05
     imp
    -0.05
    .mime
    -0.05
    POSITIVE LOGITS
    afen
    0.08
    .scalablytyped
    0.07
    OMPI
    0.07
    usted
    0.07
    adic
    0.07
    Canceled
    0.06
    adan
    0.06
     boyunca
    0.06
    oui
    0.06
    eds
    0.06
    Activations Density 0.001%

    No Known Activations