© 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. 18703
    Prev
    Next
    INDEX
    Explanations

    expressions of tolerance and endurance in relation to challenging situations

    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
    zÅij
    -0.07
    ubo
    -0.06
    itoris
    -0.06
    ucht
    -0.06
    esson
    -0.06
    rch
    -0.06
     بÙĪاسطة
    -0.06
    abouts
    -0.06
    here
    -0.06
    urai
    -0.05
    POSITIVE LOGITS
     scrutiny
    0.07
    æļ
    0.07
    ijk
    0.07
    Ø·ÙĨ
    0.07
    ardo
    0.06
     à¤Ŀ
    0.06
    aya
    0.06
     onslaught
    0.06
     tolerate
    0.06
    lope
    0.06
    Activations Density 0.020%

    No Known Activations