© 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. 42725
    Prev
    Next
    INDEX
    Explanations

    references to financial terms and conditions

    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
    åijĨ
    -0.07
    çĪµ
    -0.07
    ulong
    -0.07
    urrenc
    -0.07
     Ø®ÙĦÙģ
    -0.07
    uffman
    -0.07
    лиÑĪком
    -0.07
    zos
    -0.07
    ilip
    -0.07
    erro
    -0.07
    POSITIVE LOGITS
     penalty
    0.07
     Mellon
    0.07
     Holmes
    0.07
     gre
    0.06
     Spinner
    0.06
     Hack
    0.06
     rede
    0.06
     Hel
    0.06
     Penalty
    0.06
     unemployed
    0.06
    Activations Density 0.002%

    No Known Activations