© 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. 17-LLAMASCOPE-RES-131K
    11. 57795
    Prev
    Next
    INDEX
    Explanations

    financial and project investment details related to renewable energy

    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
    peria
    -0.07
    Ñĥки
    -0.07
    enge
    -0.07
    å½
    -0.07
    leh
    -0.07
    лини
    -0.07
     enumerable
    -0.06
     #__
    -0.06
     subsequ
    -0.06
    ectl
    -0.06
    POSITIVE LOGITS
     project
    0.09
     plant
    0.08
     projet
    0.07
     projects
    0.06
     пÑĢоекÑĤ
    0.06
    äter
    0.06
     foreigners
    0.06
     plants
    0.06
     Project
    0.06
     BOOT
    0.06
    Activations Density 0.013%

    No Known Activations