© 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. 78546
    Prev
    Next
    INDEX
    Explanations

    HTML and CSS-related syntax or structure

    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
    ertino
    -0.09
     zbo
    -0.08
    GINE
    -0.08
     Giám
    -0.07
    .Reporting
    -0.07
     jedna
    -0.07
    iele
    -0.07
    تاÙĨ
    -0.07
     tuyên
    -0.07
    Ìģc
    -0.07
    POSITIVE LOGITS
    ep
    0.06
    osh
    0.06
    oman
    0.06
    otes
    0.05
     ↵
    0.05
    ëıĮ
    0.05
     bore
    0.05
    ered
    0.05
    aggi
    0.05
    ÃŃn
    0.05
    Activations Density 0.074%

    No Known Activations