© 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. 18620
    Prev
    Next
    INDEX
    Explanations

    temporal references and specific historical moments

    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
    borg
    -0.09
    lectic
    -0.08
    /fw
    -0.07
    ezier
    -0.07
    acus
    -0.07
    gear
    -0.07
     fkk
    -0.07
    elsing
    -0.07
    aign
    -0.07
    CGColor
    -0.07
    POSITIVE LOGITS
     internet
    0.08
     Internet
    0.07
    992
    0.07
    internet
    0.06
     computers
    0.06
    552
    0.06
    218
    0.06
     Pr
    0.06
     digital
    0.06
    ilos
    0.06
    Activations Density 0.037%

    No Known Activations