© 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. 57756
    Prev
    Next
    INDEX
    Explanations

    references to geographical features, specifically grasslands and prairies

    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
    zell
    -0.07
    èµĦæł¼
    -0.07
    гл
    -0.07
    urg
    -0.07
    ght
    -0.07
    Emer
    -0.06
    caff
    -0.06
    sak
    -0.06
    chez
    -0.06
     lá»ĩ
    -0.06
    POSITIVE LOGITS
     grass
    0.07
    -transitional
    0.07
     fields
    0.07
    argar
    0.07
    stead
    0.07
    land
    0.07
    igel
    0.06
    eron
    0.06
    -edge
    0.06
    grass
    0.06
    Activations Density 0.018%

    No Known Activations