© 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. 87825
    Prev
    Next
    INDEX
    Explanations

    references to the Magento framework within the text

    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
    geh
    -0.07
    inz
    -0.07
    ÑģÑı
    -0.07
    lessness
    -0.07
     mạng
    -0.06
    nd
    -0.06
    ISCO
    -0.06
     commod
    -0.06
    .WinForms
    -0.06
    lož
    -0.06
    POSITIVE LOGITS
    \Framework
    0.09
    alim
    0.07
    ician
    0.06
    zell
    0.06
     Marks
    0.06
    lav
    0.06
    à¥ĭष
    0.06
    hur
    0.06
    ÑģÑĤан
    0.06
    imized
    0.06
    Activations Density 0.001%

    No Known Activations