© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 38584
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "now."

    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
     ìķĦì§ģ
    -0.09
    still
    -0.08
     ÙĩÙĨÙĪز
    -0.07
     then
    -0.07
     Still
    -0.07
     still
    -0.07
     à¤ħà¤Ń
    -0.07
    then
    -0.07
    idal
    -0.07
     ainda
    -0.07
    POSITIVE LOGITS
    adays
    0.08
    ished
    0.07
    aday
    0.07
    days
    0.07
     fully
    0.06
    ise
    0.06
    ZE
    0.06
    umber
    0.06
    casting
    0.06
    stderr
    0.06
    Activations Density 0.028%

    No Known Activations