© 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. 15-LLAMASCOPE-RES-131K
    11. 26643
    Prev
    Next
    INDEX
    Explanations

    instances of superclass or inheritance in object-oriented programming concepts

    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
    hiba
    -0.06
    subclass
    -0.06
    зи
    -0.06
    kor
    -0.06
    .sid
    -0.06
    емо
    -0.06
    _Map
    -0.06
    ãĥªãĥ³
    -0.06
    -map
    -0.06
    _syntax
    -0.06
    POSITIVE LOGITS
    ackers
    0.08
    acker
    0.08
    most
    0.07
    виÑī
    0.07
     addCriterion
    0.07
    oen
    0.07
    oard
    0.07
    boom
    0.07
    539
    0.07
    /base
    0.07
    Activations Density 0.007%

    No Known Activations