© 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 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. 40544
    Prev
    Next
    INDEX
    Explanations

    information related to ecological distribution and biodiversity studies

    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
     Desert
    -0.10
     desert
    -0.10
     Plains
    -0.08
     Mongolia
    -0.07
     Frost
    -0.07
     Kazakhstan
    -0.07
     Wyoming
    -0.07
     camel
    -0.07
     Sed
    -0.07
     Salt
    -0.07
    POSITIVE LOGITS
     jungle
    0.12
     forest
    0.12
     rain
    0.12
     Rain
    0.12
    forest
    0.11
     banana
    0.10
     Jungle
    0.10
     Amazon
    0.10
     rừng
    0.10
     rainy
    0.10
    Activations Density 0.139%

    No Known Activations