© 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. 69942
    Prev
    Next
    INDEX
    Explanations

    mentions of critical moments and key plays in sports events

    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
    zeichnet
    -0.06
    nim
    -0.06
    .reporting
    -0.06
    bsolute
    -0.06
    .Compose
    -0.06
     Mim
    -0.06
     halfway
    -0.06
    olang
    -0.06
    top
    -0.06
    owl
    -0.06
    POSITIVE LOGITS
    ìī
    0.07
    rame
    0.07
    .Lib
    0.07
    ãĥıãĤ¤
    0.06
    lanma
    0.06
    ë
    0.06
    inha
    0.06
    ÙĤاء
    0.06
    ÃŃž
    0.06
    lanmÄ±ÅŁ
    0.06
    Activations Density 0.021%

    No Known Activations