© 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. 91728
    Prev
    Next
    INDEX
    Explanations

    references to historical structures and architecture

    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
     dated
    -0.12
     dating
    -0.09
     Dating
    -0.09
    195
    -0.08
    ByVersion
    -0.08
    .ศ
    -0.08
    196
    -0.07
     ancient
    -0.07
    ocator
    -0.07
    Dating
    -0.07
    POSITIVE LOGITS
    Å¡ov
    0.08
    unce
    0.07
    chia
    0.07
    wal
    0.06
    ÙĪÛĮÙĩ
    0.06
    _pagination
    0.06
     evid
    0.06
    ibble
    0.06
    unj
    0.06
    ansion
    0.06
    Activations Density 0.037%

    No Known Activations