© 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. 31457
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time or specific time references

    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
     tonight
    -0.08
     tomorrow
    -0.08
    elong
    -0.08
     yesterday
    -0.07
     ÑģÑĮогоднÑĸ
    -0.07
     lately
    -0.07
    ä»Ĭ
    -0.07
     today
    -0.06
     recent
    -0.06
     Yesterday
    -0.06
    POSITIVE LOGITS
    200
    0.10
    201
    0.10
    199
    0.09
    Eventually
    0.08
     Eventually
    0.08
     roce
    0.08
     eventually
    0.08
     nÄĥm
    0.07
    198
    0.07
    195
    0.07
    Activations Density 0.029%

    No Known Activations