© 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. 15851
    Prev
    Next
    INDEX
    Explanations

    descriptions of invasive plant species 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
    trees
    -0.07
    .fig
    -0.07
    387
    -0.07
    jak
    -0.07
    .createClass
    -0.07
     Leisure
    -0.07
    ansom
    -0.07
    lux
    -0.07
     chÃŃ
    -0.07
     leisure
    -0.07
    POSITIVE LOGITS
     brows
    0.06
     attracts
    0.06
     sou
    0.06
    onec
    0.05
     Butter
    0.05
    loys
    0.05
    gm
    0.05
    Browse
    0.05
    note
    0.05
     magnets
    0.05
    Activations Density 0.009%

    No Known Activations