© 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. 4894
    Prev
    Next
    INDEX
    Explanations

    references to food safety and public health issues

    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
    uard
    -0.08
    imu
    -0.08
    _ACL
    -0.07
    fty
    -0.07
    adÃŃ
    -0.07
    bote
    -0.07
     muh
    -0.07
    .SDK
    -0.07
    olas
    -0.07
    aney
    -0.07
    POSITIVE LOGITS
     traced
    0.09
     traceback
    0.08
     trace
    0.07
     dissemination
    0.07
     contamination
    0.07
     food
    0.06
    odel
    0.06
     diarr
    0.06
     contaminated
    0.06
    trace
    0.06
    Activations Density 0.018%

    No Known Activations