© 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. 22-LLAMASCOPE-RES-131K
    11. 3898
    Prev
    Next
    INDEX
    Explanations

    references to pesticide usage and its impact on bees and pollinators

    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
    maal
    -0.06
    ieval
    -0.06
    exus
    -0.06
    ugas
    -0.06
     Mush
    -0.06
    igators
    -0.06
    agma
    -0.06
     forestry
    -0.06
     Bak
    -0.06
     UNIX
    -0.06
    POSITIVE LOGITS
     poll
    0.10
    habi
    0.08
     hosp
    0.08
    ãģ£ãģı
    0.07
     monarch
    0.07
    poll
    0.07
     Poll
    0.07
     native
    0.07
     attract
    0.07
    cts
    0.07
    Activations Density 0.013%

    No Known Activations