© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 75642
    Prev
    Next
    INDEX
    Explanations

    references to accidents or hazards involving gates and crushing incidents

    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
     Leak
    -0.08
     Patch
    -0.08
    twig
    -0.07
     patches
    -0.07
    ohn
    -0.07
    patch
    -0.07
     patch
    -0.07
    ỳ
    -0.07
    nee
    -0.07
    fusion
    -0.07
    POSITIVE LOGITS
     machine
    0.07
    Wr
    0.07
    UnitTest
    0.06
     entr
    0.06
     Entr
    0.06
    Gap
    0.06
    .machine
    0.06
    ithub
    0.06
     bree
    0.06
     Wr
    0.06
    Activations Density 0.023%

    No Known Activations