© 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. 5872
    Prev
    Next
    INDEX
    Explanations

    references to significant events or figures in history or society

    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
    UBE
    -0.08
    (æĹ¥
    -0.07
    erset
    -0.07
     lô
    -0.07
    .Criteria
    -0.07
    ή
    -0.07
    AZY
    -0.07
    اØ
    -0.07
    rů
    -0.07
     ún
    -0.07
    POSITIVE LOGITS
     arguably
    0.09
     fucking
    0.08
     basically
    0.08
     another
    0.08
     almost
    0.07
     major
    0.07
     literally
    0.07
     two
    0.07
     essentially
    0.07
     highly
    0.06
    Activations Density 0.154%

    No Known Activations