© 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. 88796
    Prev
    Next
    INDEX
    Explanations

    categories of disasters and their classifications

    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
    .override
    -0.07
    loggedin
    -0.07
     )↵↵↵↵↵↵↵↵
    -0.07
    èĤ¡ä»½
    -0.06
    égor
    -0.06
    ثر
    -0.06
    morgan
    -0.06
     Hardy
    -0.06
    ÙĪاز
    -0.06
    559
    -0.06
    POSITIVE LOGITS
     natural
    0.09
     large
    0.08
     sudden
    0.07
    natural
    0.07
     ts
    0.07
    rawer
    0.07
    large
    0.07
    dere
    0.06
     Large
    0.06
     Natural
    0.06
    Activations Density 0.016%

    No Known Activations