© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30553
    Prev
    Next
    INDEX
    Explanations

    references to object-oriented programming structure, particularly methods and properties invoked on instances

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ilde
    -0.07
    zdy
    -0.07
     rue
    -0.07
    rang
    -0.06
    utenberg
    -0.06
    haar
    -0.06
    uters
    -0.06
    ichel
    -0.06
     blown
    -0.06
    onde
    -0.06
    POSITIVE LOGITS
     ÎijÏĢ
    0.06
    747
    0.06
     Stanley
    0.06
    íĸ¥
    0.06
     gre
    0.06
    esser
    0.06
     Utf
    0.06
    347
    0.06
    Ïħ
    0.06
    .fp
    0.06
    Activations Density 0.004%

    No Known Activations