© 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. 15-LLAMASCOPE-RES-131K
    11. 87872
    Prev
    Next
    INDEX
    Explanations

    situations involving medical emergencies or health crises

    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
     Reconstruction
    -0.08
     addCriterion
    -0.08
    ardin
    -0.07
    åĤ·
    -0.07
    utt
    -0.07
    icas
    -0.07
    rego
    -0.07
    elmet
    -0.07
    елик
    -0.07
    .dex
    -0.07
    POSITIVE LOGITS
     faint
    0.07
     medical
    0.07
     Frontier
    0.06
    705
    0.06
    576
    0.06
     exp
    0.06
     falls
    0.06
     Lif
    0.06
     Alonso
    0.06
    971
    0.05
    Activations Density 0.011%

    No Known Activations