© 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. 9-LLAMASCOPE-RES-131K
    11. 94234
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and variable declarations in programming contexts

    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
    èĪį
    -0.08
    StackNavigator
    -0.08
    íĭ
    -0.08
    ãĤ¿ãĥ«
    -0.08
    amba
    -0.07
    roti
    -0.07
    ãĥ³ãĥĩãĤ£
    -0.07
    ynamo
    -0.06
     ['./
    -0.06
    anto
    -0.06
    POSITIVE LOGITS
     beep
    0.06
     Newman
    0.06
    getInstance
    0.06
    sf
    0.06
     Lance
    0.06
     Deniz
    0.06
     mue
    0.06
     dr
    0.06
    ully
    0.05
     trump
    0.05
    Activations Density 0.002%

    No Known Activations