© 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. 18726
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to code generation and autogenerated content

    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
    uest
    -0.07
     Castillo
    -0.06
    417
    -0.06
    argas
    -0.06
    tones
    -0.06
     le
    -0.05
     compl
    -0.05
    ÐłÐ¾Ð·
    -0.05
    IFS
    -0.05
     adopting
    -0.05
    POSITIVE LOGITS
    .Generated
    0.09
     èĩªåĬ¨çĶŁæĪIJ
    0.08
    sik
    0.08
    Generated
    0.07
     Generated
    0.07
     GENERATED
    0.07
    _interfaces
    0.07
    ANNEL
    0.07
    HeaderCode
    0.07
    .mybatisplus
    0.07
    Activations Density 0.002%

    No Known Activations