© 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. 29865
    Prev
    Next
    INDEX
    Explanations

    specific organizations and their relations to regulatory frameworks

    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
    ردÙĩ
    -0.08
     recent
    -0.07
    ãĥĮ
    -0.07
     dÅĻÃŃ
    -0.07
     nynÃŃ
    -0.07
    iá»ĥu
    -0.07
    ä»Ĭå¹´
    -0.07
    ,www
    -0.07
     recently
    -0.07
     lately
    -0.07
    POSITIVE LOGITS
     became
    0.10
     began
    0.09
     suddenly
    0.08
     came
    0.07
     took
    0.07
     finally
    0.07
     was
    0.07
    took
    0.07
    1
    0.07
     begin
    0.07
    Activations Density 0.098%

    No Known Activations