© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95193
    Prev
    Next
    INDEX
    Explanations

    activities and processes related to mosquito control and management

    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
     Sang
    -0.06
    .fn
    -0.06
    .cgi
    -0.06
     Dann
    -0.06
     mal
    -0.06
    ÙĪÛĮÙĩ
    -0.06
     consciousness
    -0.06
    евеÑĢ
    -0.05
    rove
    -0.05
     jo
    -0.05
    POSITIVE LOGITS
    oÄŁ
    0.07
     Guinness
    0.07
    esch
    0.07
    éij
    0.07
    HeaderCode
    0.07
     Rank
    0.07
    utan
    0.06
    Å¡tÄĽ
    0.06
    LLU
    0.06
    IRT
    0.06
    Activations Density 0.005%

    No Known Activations