© 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. 3520
    Prev
    Next
    INDEX
    Explanations

    Java methods and their associated annotations

    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
    ensen
    -0.06
     ly
    -0.06
    794
    -0.06
    SelectionMode
    -0.06
    653
    -0.06
    erdale
    -0.06
    -sizing
    -0.06
    aras
    -0.06
    BufferSize
    -0.05
     sna
    -0.05
    POSITIVE LOGITS
     unloaded
    0.07
    cus
    0.07
    arkin
    0.07
    IBC
    0.06
     anale
    0.06
    uzzi
    0.06
     Strikes
    0.06
    elik
    0.06
     polished
    0.06
    ocz
    0.06
    Activations Density 0.003%

    No Known Activations