© 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. 104053
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to coding or programming elements

    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
    asz
    -0.07
    ditor
    -0.07
    agar
    -0.06
    conomy
    -0.06
    oe
    -0.06
    amb
    -0.06
    opal
    -0.06
    .hu
    -0.06
    prm
    -0.06
    avia
    -0.06
    POSITIVE LOGITS
     addCriterion
    0.08
     Sesso
    0.07
    ERVED
    0.07
     náv
    0.07
    ÄĽÅĻ
    0.06
     vá»±c
    0.06
     øns
    0.06
    urer
    0.06
    Ø´ÙĨ
    0.06
    isper
    0.06
    Activations Density 0.001%

    No Known Activations