© 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. 18836
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to algebra and polynomial rings

    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
    nda
    -0.07
     Ariel
    -0.07
    meli
    -0.07
    erset
    -0.06
    ets
    -0.06
    quota
    -0.06
     ilan
    -0.06
    fault
    -0.06
    aepernick
    -0.06
    lius
    -0.06
    POSITIVE LOGITS
    Compat
    0.06
     base
    0.06
     residue
    0.06
     Modular
    0.06
    ilden
    0.06
     Base
    0.06
     Hancock
    0.06
    idue
    0.06
     Alphabet
    0.06
    SHOP
    0.06
    Activations Density 0.025%

    No Known Activations