© 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. 104003
    Prev
    Next
    INDEX
    Explanations

    programming or coding actions and functions

    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
    esz
    -0.06
    idea
    -0.06
    Bon
    -0.06
    ırak
    -0.06
    alent
    -0.06
    ibaba
    -0.06
    QueryParam
    -0.06
     <$>
    -0.06
    ترÛĮ
    -0.05
    iar
    -0.05
    POSITIVE LOGITS
    undler
    0.08
    ancel
    0.07
    BufferData
    0.07
    _DU
    0.07
    èª
    0.07
    í
    0.07
    yre
    0.06
     luyá»ĩn
    0.06
    yg
    0.06
    du
    0.06
    Activations Density 0.002%

    No Known Activations