Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43646
    Prev
    Next
    INDEX
    Explanations

    monetary values associated with lottery winnings or prizes

    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
    ales
    -0.07
    elsen
    -0.07
    imeo
    -0.07
     Ñģеб
    -0.06
    ubat
    -0.06
    ucus
    -0.06
    дÑĢеÑģ
    -0.06
     phái
    -0.06
    KHTML
    -0.06
    iasi
    -0.06
    POSITIVE LOGITS
     jack
    0.13
     prizes
    0.11
     jackpot
    0.11
     Jack
    0.11
     progressive
    0.11
     JACK
    0.11
    jack
    0.10
     grand
    0.10
     progressives
    0.10
     Progressive
    0.10
    Activations Density 0.018%

    No Known Activations