© 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. 116623
    Prev
    Next
    INDEX
    Explanations

    programming-related terms or structures

    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
    ιÏĩ
    -0.07
    пи
    -0.06
     duct
    -0.06
    iros
    -0.06
     Moines
    -0.06
     Duc
    -0.06
    resas
    -0.06
    olly
    -0.06
    iais
    -0.06
    .ci
    -0.06
    POSITIVE LOGITS
    AdapterFactory
    0.07
    itom
    0.07
    ersist
    0.07
    anja
    0.07
    apgolly
    0.06
    Cro
    0.06
    arte
    0.06
    .locals
    0.06
    collapse
    0.06
    iphone
    0.06
    Activations Density 0.000%

    No Known Activations