© 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. 88207
    Prev
    Next
    INDEX
    Explanations

    terms related to injury prevention and safety measures

    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
    VRT
    -0.07
     Davis
    -0.06
     transform
    -0.06
     ActionTypes
    -0.06
     dabei
    -0.05
    maz
    -0.05
    Äįky
    -0.05
    aton
    -0.05
    orea
    -0.05
    eft
    -0.05
    POSITIVE LOGITS
    ç·Ĵ
    0.07
    ylko
    0.07
    achuset
    0.07
    JE
    0.07
    ик
    0.07
    ès
    0.07
     Examiner
    0.07
     INTERRUPTION
    0.06
    âĹİ
    0.06
    .eql
    0.06
    Activations Density 0.022%

    No Known Activations