© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 123402
    Prev
    Next
    INDEX
    Explanations

    terms related to infectious diseases and their management

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     probes
    -0.07
     suicidal
    -0.07
    velte
    -0.06
     gas
    -0.06
     probe
    -0.06
    probe
    -0.06
    ết
    -0.06
    caret
    -0.06
    гл
    -0.06
     om
    -0.06
    POSITIVE LOGITS
    avel
    0.09
    andi
    0.08
     endemic
    0.07
     Redemption
    0.07
     villages
    0.07
    èm
    0.07
    isay
    0.07
     Serg
    0.07
    Cheap
    0.07
    opup
    0.06
    Activations Density 0.009%

    No Known Activations