© 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. 91737
    Prev
    Next
    INDEX
    Explanations

    programming structures and error-handling patterns in code

    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
    703
    -0.06
    ãĥĥ
    -0.06
    bek
    -0.06
    pla
    -0.06
    asaki
    -0.06
     Fade
    -0.06
     slap
    -0.06
     Sass
    -0.06
    andex
    -0.06
    iyel
    -0.06
    POSITIVE LOGITS
     afterEach
    0.09
    tearDown
    0.07
     teardown
    0.07
     tearDown
    0.07
     Closing
    0.07
     closing
    0.06
    .cleanup
    0.06
    .END
    0.06
     Karlov
    0.06
    ardown
    0.06
    Activations Density 0.003%

    No Known Activations