© 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. 17-LLAMASCOPE-RES-131K
    11. 87389
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating possibility, necessity, and predictions about actions

    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
     plá
    -0.08
     vyh
    -0.07
    ÐĴС
    -0.07
    PIX
    -0.07
     mặt
    -0.07
    achs
    -0.07
     pás
    -0.07
     chá»ĭu
    -0.07
    efon
    -0.07
    uggy
    -0.07
    POSITIVE LOGITS
     helps
    0.10
     help
    0.10
     ensures
    0.07
     Help
    0.07
    help
    0.07
    igo
    0.07
     ensure
    0.07
     Yield
    0.07
     allows
    0.06
     Helps
    0.06
    Activations Density 0.038%

    No Known Activations