© 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. 15-LLAMASCOPE-RES-131K
    11. 85988
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that link multiple concepts together

    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
    reopen
    -0.08
    /close
    -0.07
    rame
    -0.07
    ýn
    -0.07
    iaux
    -0.07
    oup
    -0.07
    éĺª
    -0.07
    ÙĪار
    -0.07
     initData
    -0.07
     GOODMAN
    -0.07
    POSITIVE LOGITS
    /or
    0.09
    als
    0.07
    ist
    0.06
    ayed
    0.06
    ispers
    0.06
    ãĥ³ãĤ¸
    0.06
    atum
    0.06
    acles
    0.06
     re
    0.05
     subsequent
    0.05
    Activations Density 0.106%

    No Known Activations