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

    Neuronpedia

    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. 127474
    Prev
    Next
    INDEX
    Explanations

    references to object equality and comparison in 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
     Král
    -0.08
    ALAR
    -0.08
    ë§ī
    -0.08
    aille
    -0.07
    itzer
    -0.07
    OffsetTable
    -0.07
    ogene
    -0.07
     ÐĹаг
    -0.07
    amburger
    -0.07
    ARRY
    -0.07
    POSITIVE LOGITS
     Equality
    0.09
     identity
    0.09
    Equality
    0.08
     equality
    0.08
    memcmp
    0.08
     Identity
    0.08
    hashCode
    0.07
    EqualityComparer
    0.07
     comparison
    0.07
     comparing
    0.07
    Activations Density 0.024%

    No Known Activations