© 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 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. 76614
    Prev
    Next
    INDEX
    Explanations

    topics related to sports events, highlights, and updates

    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
    roup
    -0.07
    .openConnection
    -0.06
     Braz
    -0.06
     éĥ
    -0.06
    念
    -0.06
    _coeffs
    -0.06
    æ´
    -0.06
    Defs
    -0.06
     Hemisphere
    -0.06
    ä¸Ģå¹´
    -0.06
    POSITIVE LOGITS
    æĮ¯ãĤĬ
    0.07
    Reaction
    0.07
    /result
    0.07
    afs
    0.07
    zet
    0.07
    reaction
    0.07
     coverage
    0.07
    udas
    0.07
     Game
    0.07
     Reaction
    0.07
    Activations Density 0.028%

    No Known Activations