© 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. 56187
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structures in code

    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
    mpar
    -0.07
    ordion
    -0.07
     dá
    -0.07
    wnd
    -0.07
    нг
    -0.07
    баÑĩ
    -0.07
    ALSE
    -0.07
    BUG
    -0.07
    ntag
    -0.07
    pillar
    -0.07
    POSITIVE LOGITS
     head
    0.09
     Head
    0.09
     chain
    0.08
    _head
    0.08
    Head
    0.08
     node
    0.07
    head
    0.07
    (head
    0.07
     Link
    0.07
     Chain
    0.07
    Activations Density 0.016%

    No Known Activations