© 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. 61036
    Prev
    Next
    INDEX
    Explanations

    keywords related to emergency services and health care system issues

    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
    ypad
    -0.09
    еви
    -0.08
    723
    -0.08
    onna
    -0.07
    Âł↵↵
    -0.07
    quette
    -0.07
    ¯¯¯¯
    -0.07
    лоп
    -0.07
    (æĹ¥
    -0.07
    ContentLoaded
    -0.07
    POSITIVE LOGITS
    )
    0.08
    ~
    0.07
     than
    0.07
    ),
    0.07
     âĢ¢
    0.07
    ]
    0.06
    than
    0.06
    ~~
    0.06
     would
    0.06
     will
    0.06
    Activations Density 4.028%

    No Known Activations