© 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. 130731
    Prev
    Next
    INDEX
    Explanations

    colon-separated lists or structured data formatting

    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
    heed
    -0.06
    Interop
    -0.06
    Ø´
    -0.06
    uce
    -0.06
     ÅŁun
    -0.06
    ä»Ģ
    -0.06
    ìŀIJìĿ¸
    -0.06
     rift
    -0.06
    оди
    -0.06
    _fatal
    -0.06
    POSITIVE LOGITS
    ä¸Ģç§į
    0.09
     another
    0.07
    ä¸ĢåĢĭ
    0.07
    ä¸Ģ个
    0.07
     Another
    0.07
    Mui
    0.06
    Feat
    0.06
    itet
    0.06
    rescia
    0.06
     eine
    0.06
    Activations Density 0.017%

    No Known Activations