© 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. 2800
    Prev
    Next
    INDEX
    Explanations

    references to types of plants and their characteristics

    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
    izzato
    -0.07
     drown
    -0.06
     Wheat
    -0.06
     drowning
    -0.06
     machine
    -0.06
    yme
    -0.06
     Soy
    -0.06
     grains
    -0.06
    uddy
    -0.06
    idle
    -0.06
    POSITIVE LOGITS
     Mesa
    0.09
     Sunset
    0.07
     Desert
    0.07
     Petra
    0.07
    ÅĻad
    0.07
     Lust
    0.07
     desert
    0.07
    aylight
    0.07
    /UIKit
    0.07
     caut
    0.07
    Activations Density 0.004%

    No Known Activations