© 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. 5372
    Prev
    Next
    INDEX
    Explanations

    concepts related to urban development and health management solutions

    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
    Å¡ov
    -0.06
     barely
    -0.06
    Ware
    -0.06
     usually
    -0.06
    ä¹ĭä¸Ģ
    -0.06
     Eigen
    -0.05
     Alternate
    -0.05
    yna
    -0.05
    usually
    -0.05
     amb
    -0.05
    POSITIVE LOGITS
     other
    0.19
     similarly
    0.16
    other
    0.16
     similar
    0.15
     future
    0.14
     otros
    0.14
    åħ¶ä»ĸ
    0.13
     anderen
    0.13
     andere
    0.13
     otras
    0.13
    Activations Density 0.046%

    No Known Activations