© 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. 120499
    Prev
    Next
    INDEX
    Explanations

    phrases related to high-level discussions or policies regarding radioactive waste management

    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
    ew
    -0.09
     Jennings
    -0.07
     Setter
    -0.07
    ancellable
    -0.07
    elf
    -0.07
    ewolf
    -0.07
    竹
    -0.07
    eton
    -0.07
    adic
    -0.07
     herk
    -0.07
    POSITIVE LOGITS
    -level
    0.10
    /high
    0.08
     level
    0.07
    -Level
    0.07
    /top
    0.07
    led
    0.07
    -most
    0.07
    âĢĮترÛĮÙĨ
    0.06
    utar
    0.06
    ertz
    0.06
    Activations Density 0.008%

    No Known Activations