© 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. 42769
    Prev
    Next
    INDEX
    Explanations

    instances of significant days or events and their impacts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     nightly
    -0.06
    ese
    -0.06
    ابة
    -0.06
    grave
    -0.06
    hip
    -0.06
    æľŁéĸĵ
    -0.06
    amo
    -0.06
    年代
    -0.06
     bang
    -0.06
    acer
    -0.06
    POSITIVE LOGITS
    /day
    0.10
     day
    0.09
     spent
    0.09
    -day
    0.09
    day
    0.09
     DAY
    0.08
    (day
    0.08
    DAY
    0.08
    .day
    0.08
     Day
    0.08
    Activations Density 0.046%

    No Known Activations