© 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. 74300
    Prev
    Next
    INDEX
    Explanations

    references to the "Star Trek" and "Star Wars" franchises

    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
    osis
    -0.07
    ergus
    -0.06
    æ´¥
    -0.06
     تص
    -0.06
     Tale
    -0.06
     tslib
    -0.06
    ãĥ
    -0.06
    Ø´
    -0.06
    ismet
    -0.06
    hed
    -0.06
    POSITIVE LOGITS
     series
    0.07
     Schwarz
    0.07
    oga
    0.07
    arLayout
    0.07
    ibrator
    0.06
    flater
    0.06
    -series
    0.06
    ÙĪات
    0.06
    .removeListener
    0.06
    Um
    0.06
    Activations Density 0.016%

    No Known Activations