© 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. 127329
    Prev
    Next
    INDEX
    Explanations

    content related to workplace health and safety practices

    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
     IID
    -0.07
    enstein
    -0.06
     Beh
    -0.06
     Zuk
    -0.06
    úp
    -0.06
    ccoli
    -0.06
    ↵↵
    -0.06
     Zw
    -0.05
     mour
    -0.05
     De
    -0.05
    POSITIVE LOGITS
    isque
    0.07
    ooks
    0.07
    ownik
    0.06
    SETS
    0.06
    ãĥĸãĥŃ
    0.06
    voices
    0.06
    à¤Ĥश
    0.06
     POSSIBILITY
    0.06
    emiz
    0.06
     е
    0.06
    Activations Density 0.005%

    No Known Activations