© 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. 103412
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs and operations

    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
    VK
    -0.07
    achable
    -0.07
    warts
    -0.06
    orus
    -0.06
    STA
    -0.06
    ìŀ¡
    -0.06
    vere
    -0.06
     initializer
    -0.06
    ivas
    -0.06
    Teachers
    -0.06
    POSITIVE LOGITS
    .mutable
    0.07
    _updates
    0.07
     alter
    0.07
    .setParameter
    0.07
     change
    0.07
    change
    0.07
    .modify
    0.07
    alli
    0.07
    (change
    0.07
     UPDATE
    0.07
    Activations Density 0.031%

    No Known Activations