© 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. 96190
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps related to significant events

    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
     вÑĩ
    -0.09
    ISIBLE
    -0.08
    resi
    -0.08
    incinn
    -0.08
    (çģ«
    -0.08
    ulist
    -0.07
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
    .Localization
    -0.07
    _recent
    -0.07
    POSITIVE LOGITS
     next
    0.13
     tomorrow
    0.12
    next
    0.11
     upcoming
    0.10
     future
    0.09
    (next
    0.09
    -next
    0.08
    _next
    0.08
    .next
    0.08
     NEXT
    0.08
    Activations Density 0.031%

    No Known Activations