© 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. 106690
    Prev
    Next
    INDEX
    Explanations

    code-related operations and functions

    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
     repe
    -0.06
     lon
    -0.06
    ame
    -0.06
    ourg
    -0.06
    9
    -0.06
    alis
    -0.06
    à¥Īम
    -0.05
     parach
    -0.05
     bow
    -0.05
     cheek
    -0.05
    POSITIVE LOGITS
    _passwd
    0.08
    ãģ¯ãģļ
    0.07
    æ
    0.07
    第ä¸ī
    0.07
    porno
    0.07
    .second
    0.06
    第äºĮ
    0.06
    íĬ¹ë³Ħ
    0.06
    egis
    0.06
    :System
    0.06
    Activations Density 0.008%

    No Known Activations