© 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. 106523
    Prev
    Next
    INDEX
    Explanations

    phrases related to public perception and rumor

    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
     currently
    -0.10
    currently
    -0.09
     presently
    -0.09
    缮åīį
    -0.09
     tomorrow
    -0.08
     tonight
    -0.08
     Currently
    -0.08
    Currently
    -0.08
     now
    -0.08
     CURRENT
    -0.07
    POSITIVE LOGITS
     whenever
    0.12
     during
    0.10
     sometimes
    0.10
     ëĭ¹ìĭľ
    0.09
     ÙĪÙĥاÙĨ
    0.09
     durante
    0.09
     Whenever
    0.09
    ãģĹãģ¦ãģĦãģŁ
    0.09
    Whenever
    0.09
     tehdy
    0.09
    Activations Density 0.082%

    No Known Activations