© 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. 3684
    Prev
    Next
    INDEX
    Explanations

    terms related to various biological classifications and virus families

    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
    ItemAt
    -0.08
    elden
    -0.07
    stadt
    -0.07
    undy
    -0.07
    efon
    -0.07
    .LayoutStyle
    -0.07
    untas
    -0.07
    otland
    -0.06
    ãĥ¼ãĥŀ
    -0.06
    ollapsed
    -0.06
    POSITIVE LOGITS
    idae
    0.11
    aceae
    0.10
     family
    0.09
     Family
    0.08
    orida
    0.07
    .family
    0.07
     Familie
    0.07
    วà¸ĩศ
    0.07
    ropoda
    0.07
     inc
    0.07
    Activations Density 0.016%

    No Known Activations