© 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. 42721
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs and operations

    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
    indow
    -0.07
     rig
    -0.07
    aus
    -0.06
     Darling
    -0.06
    habi
    -0.06
    wheel
    -0.06
     inherited
    -0.06
    owell
    -0.06
    rig
    -0.05
     Crosby
    -0.05
    POSITIVE LOGITS
    (()
    0.14
    >(()
    0.11
     (()
    0.09
     Runnable
    0.08
    (||
    0.08
     ^{↵
    0.08
    :^{↵
    0.08
     lambda
    0.07
    (lambda
    0.07
    	func
    0.07
    Activations Density 0.044%

    No Known Activations