© 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. 116336
    Prev
    Next
    INDEX
    Explanations

    instructions related to precision and detail in tasks

    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
     hữu
    -0.07
    yš
    -0.06
    unicipio
    -0.06
    avers
    -0.06
    tone
    -0.06
     pazar
    -0.06
    -tree
    -0.06
    ceeded
    -0.06
     danmark
    -0.06
    URA
    -0.06
    POSITIVE LOGITS
     when
    0.07
     memor
    0.07
     whenever
    0.07
     exactly
    0.06
     Kad
    0.06
     Memor
    0.06
     follow
    0.06
    monitor
    0.06
     cuck
    0.06
     watch
    0.06
    Activations Density 0.023%

    No Known Activations