© 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. 80225
    Prev
    Next
    INDEX
    Explanations

    information regarding food safety and health risks associated with eating certain items

    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
    enegro
    -0.07
    ENU
    -0.07
    ssel
    -0.07
     mạch
    -0.06
    ois
    -0.06
    ÏĮγ
    -0.06
    inker
    -0.06
    olu
    -0.06
    æŀ
    -0.06
    виÑĩай
    -0.06
    POSITIVE LOGITS
     risk
    0.08
    -safe
    0.07
     Pik
    0.07
     Unsafe
    0.07
     bacter
    0.07
     Transmission
    0.07
    Transmission
    0.07
     unsafe
    0.07
     Risk
    0.07
     risks
    0.06
    Activations Density 0.005%

    No Known Activations