© 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. 15-LLAMASCOPE-RES-131K
    11. 295
    Prev
    Next
    INDEX
    Explanations

    references to prairie landscapes and related geographical features

    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
    holes
    -0.06
    chez
    -0.06
    hole
    -0.06
    èµĦæł¼
    -0.06
    imb
    -0.06
    urg
    -0.06
    sburg
    -0.06
    æ³ī
    -0.06
    pos
    -0.06
    reek
    -0.06
    POSITIVE LOGITS
    üstü
    0.07
    kate
    0.07
    enne
    0.07
    ovÃŃ
    0.07
    land
    0.07
     khô
    0.07
    osal
    0.07
    asar
    0.07
    -transitional
    0.07
    ÑĢави
    0.07
    Activations Density 0.011%

    No Known Activations