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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119195
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures, particularly in the context of object-oriented programming and application logic

    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
    olik
    -0.08
    iliz
    -0.07
    .xz
    -0.06
     Sle
    -0.06
    .serializer
    -0.06
    reopen
    -0.06
     Locate
    -0.06
    ancia
    -0.06
    atism
    -0.06
    OfClass
    -0.06
    POSITIVE LOGITS
    æħİ
    0.07
    evin
    0.07
    eydi
    0.06
    riel
    0.06
    ether
    0.06
    ureau
    0.06
     {{--<
    0.06
     Abyss
    0.06
    оÑĢо
    0.06
    meden
    0.06
    Activations Density 0.010%

    No Known Activations