© 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. 61041
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental justice and community impact

    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
    çļĦä¸Ģ个
    -0.07
     èĬ
    -0.07
     ÙĪÙĩÙĪ
    -0.07
    æĺ¯ä¸Ģ个
    -0.07
    Ø®ÙĪاÙĨ
    -0.07
    Ä°s
    -0.06
    podob
    -0.06
    Ø°ÙĬ
    -0.06
     дÑĢÑĥга
    -0.06
    .getOwnPropertyDescriptor
    -0.06
    POSITIVE LOGITS
     both
    0.20
    both
    0.18
     BOTH
    0.14
    åĪĨåĪ«
    0.14
     både
    0.13
     respectively
    0.13
     two
    0.12
    Both
    0.12
     Both
    0.12
     beiden
    0.12
    Activations Density 0.133%

    No Known Activations