© 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 EvalsExportsinterp-engineNEWAPI 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. 2554
    Prev
    Next
    INDEX
    Explanations

    descriptions of weather conditions and their impact on activities

    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
     åĥ
    -0.07
     recurs
    -0.06
     independents
    -0.06
    ç¹ģ
    -0.06
    боÑĤ
    -0.06
     overseas
    -0.06
     Defence
    -0.05
     rainy
    -0.05
     HANDLE
    -0.05
    å¤ĩ
    -0.05
    POSITIVE LOGITS
    pii
    0.07
     Shield
    0.07
    -transitional
    0.07
    indr
    0.07
    vest
    0.07
    imore
    0.07
    ewis
    0.07
    -toggle
    0.07
    åįĪ
    0.06
    ilan
    0.06
    Activations Density 0.012%

    No Known Activations