© 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. 69015
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to email attachments

    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
    iling
    -0.06
    748
    -0.06
    Compilation
    -0.06
    jal
    -0.06
    illing
    -0.06
     Burgess
    -0.05
    847
    -0.05
    er
    -0.05
    937
    -0.05
    ider
    -0.05
    POSITIVE LOGITS
     attachments
    0.09
     첨ë¶Ģ
    0.08
    media
    0.08
    ìĭ¤
    0.08
    æ·»
    0.07
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    0.07
    attachments
    0.07
    Attachments
    0.07
    roulette
    0.07
    SizePolicy
    0.07
    Activations Density 0.018%

    No Known Activations