© 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. 27770
    Prev
    Next
    INDEX
    Explanations

    specific terms related to epidemic models and their thresholds

    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
    dress
    -0.07
     dress
    -0.07
    vod
    -0.06
    ervo
    -0.06
    Ïĥο
    -0.06
    nton
    -0.06
    hydration
    -0.06
    hei
    -0.06
     Dress
    -0.06
     dressing
    -0.06
    POSITIVE LOGITS
     Mathematical
    0.07
    IMS
    0.07
    .bio
    0.07
     Zombies
    0.07
     Modeling
    0.07
    _Model
    0.07
     model
    0.07
     bi
    0.07
     Controllers
    0.07
     Growth
    0.07
    Activations Density 0.085%

    No Known Activations