© 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 EvalsExportsAPI 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. 89238
    Prev
    Next
    INDEX
    Explanations

    keywords associated with the Zika virus and its implications on health

    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
    OU
    -0.07
    viz
    -0.07
    impan
    -0.07
    abd
    -0.07
    IRM
    -0.07
    er
    -0.07
    UA
    -0.07
    imler
    -0.07
    itur
    -0.07
    neau
    -0.06
    POSITIVE LOGITS
     disease
    0.07
    zcze
    0.07
     Lyme
    0.07
    otta
    0.07
     Overs
    0.06
    305
    0.06
    iores
    0.06
     Disease
    0.06
    383
    0.06
    ians
    0.06
    Activations Density 0.000%

    No Known Activations