© 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 EvalsExportsinterp-engineNEWAPI 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. 42053
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental consulting and climate risk 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
    agas
    -0.07
    addtogroup
    -0.07
    ProcessEvent
    -0.07
    aga
    -0.07
     blok
    -0.07
    .dtd
    -0.06
    éĽĦ
    -0.06
     obÄĽ
    -0.06
    scanner
    -0.06
    ãģ¦ãĤĭ
    -0.06
    POSITIVE LOGITS
     civil
    0.09
     consulting
    0.09
     engineers
    0.09
     engineer
    0.09
     Engineers
    0.09
     engineering
    0.09
     consultants
    0.09
     consultant
    0.09
     Civil
    0.09
     Consulting
    0.08
    Activations Density 0.042%

    No Known Activations