© 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. 84230
    Prev
    Next
    INDEX
    Explanations

    references to specific chemical compounds

    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
     leak
    -0.08
     leaks
    -0.08
     åı·
    -0.07
     Leak
    -0.07
    lac
    -0.07
    æĭ³
    -0.07
    ÑĢаб
    -0.07
    LEASE
    -0.06
    IOC
    -0.06
    .DialogResult
    -0.06
    POSITIVE LOGITS
    ANGO
    0.06
    Aceptar
    0.06
    ounter
    0.06
    idar
    0.06
     perse
    0.06
    uitar
    0.06
    ["@
    0.06
     اÙĦتس
    0.06
     Sadd
    0.06
     Gamb
    0.06
    Activations Density 0.000%

    No Known Activations