© 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. 9-LLAMASCOPE-RES-131K
    11. 96593
    Prev
    Next
    INDEX
    Explanations

    connections and patterns in player statistics and achievements across various sports

    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
     Hughes
    -0.07
     counters
    -0.06
    ikip
    -0.06
    -counter
    -0.06
    Hugh
    -0.06
     fark
    -0.05
    _tensors
    -0.05
    /products
    -0.05
    mes
    -0.05
     speci
    -0.05
    POSITIVE LOGITS
    gow
    0.07
    AndView
    0.07
    antine
    0.07
    PointerException
    0.06
    .snap
    0.06
     اÙĦعÙĤ
    0.06
    vell
    0.06
    sitemap
    0.06
    ãĥ©ãĤ¯
    0.06
    utz
    0.06
    Activations Density 0.029%

    No Known Activations