© 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. 121450
    Prev
    Next
    INDEX
    Explanations

    mentions of communication and information exchange

    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
     clock
    -0.06
    ellipsis
    -0.06
    çķ¥
    -0.06
     ell
    -0.06
    erve
    -0.06
     scenic
    -0.06
     Ell
    -0.06
    ellen
    -0.06
     Assembly
    -0.06
     Moor
    -0.06
    POSITIVE LOGITS
    å°±ä¼ļ
    0.09
    ä¼ļ
    0.08
    æľĥ
    0.07
     will
    0.07
     sẽ
    0.07
    will
    0.07
    isci
    0.07
     ä¼ļ
    0.07
    \Bridge
    0.07
    íķĺë©´
    0.07
    Activations Density 0.049%

    No Known Activations