© 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. 26855
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical symbols and notations

    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
    edir
    -0.08
    erable
    -0.08
    edata
    -0.07
    iteDatabase
    -0.07
    umn
    -0.07
    anos
    -0.07
    erli
    -0.07
    umno
    -0.07
    зÑĥ
    -0.07
    ETO
    -0.07
    POSITIVE LOGITS
     Bew
    0.07
     squared
    0.06
    ville
    0.06
     sized
    0.06
    cope
    0.06
    æĿ¯
    0.06
    URATION
    0.06
     vulgar
    0.06
     Lind
    0.05
    -sized
    0.05
    Activations Density 0.112%

    No Known Activations