© 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 EvalsExportsAPI 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. 58642
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "super" and related concepts in programming, particularly in object-oriented programming contexts

    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
    ãĥŃãĥ¼
    -0.08
     -
    -0.06
     Hib
    -0.06
    arry
    -0.06
    stdarg
    -0.06
     Protein
    -0.06
     Mayer
    -0.05
     ê
    -0.05
    .loader
    -0.05
     lik
    -0.05
    POSITIVE LOGITS
    ivery
    0.08
    ÑĢап
    0.08
    ynamo
    0.07
    ë§ī
    0.07
    оÑĢоÑĤ
    0.07
    agina
    0.07
    /internal
    0.07
    elerik
    0.07
    _datos
    0.07
    -ÑĤаки
    0.07
    Activations Density 0.002%

    No Known Activations