© 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. 69021
    Prev
    Next
    INDEX
    Explanations

    references to specific commemorative events or important observances

    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
    urette
    -0.10
    ulpt
    -0.09
    acomment
    -0.08
    eca
    -0.07
    atical
    -0.07
    noticed
    -0.07
    venience
    -0.07
     güncel
    -0.07
     milano
    -0.07
    çuk
    -0.07
    POSITIVE LOGITS
     Ley
    0.07
     Nos
    0.07
     hol
    0.06
     Cohen
    0.06
    zo
    0.06
    nos
    0.06
    usta
    0.06
    Nos
    0.06
     Day
    0.05
    rame
    0.05
    Activations Density 0.002%

    No Known Activations