© 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. 17-LLAMASCOPE-RES-131K
    11. 107282
    Prev
    Next
    INDEX
    Explanations

    references to the "Jurassic Park" movie franchise and its cast

    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
    lep
    -0.08
    elenium
    -0.07
    بÙĩ
    -0.07
    clk
    -0.07
     PIXI
    -0.06
     bil
    -0.06
    jez
    -0.06
    ανά
    -0.06
    AZE
    -0.06
    JNI
    -0.06
    POSITIVE LOGITS
     Jurassic
    0.10
     dinosaur
    0.07
     dinosaurs
    0.07
    osaurs
    0.07
     Site
    0.06
     Amp
    0.06
    preh
    0.06
    inosaur
    0.06
     fossil
    0.06
     Universal
    0.06
    Activations Density 0.011%

    No Known Activations