© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3069
    Prev
    Next
    INDEX
    Explanations

    content related to natural disasters and their consequences

    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
     Aires
    -0.07
    olith
    -0.07
     fal
    -0.06
    ÙĤر
    -0.06
    zon
    -0.06
     barren
    -0.06
    witch
    -0.06
    имÑĥ
    -0.06
    غاز
    -0.06
     Fal
    -0.06
    POSITIVE LOGITS
     flood
    0.14
     flooding
    0.12
     Flood
    0.12
     floods
    0.11
     inund
    0.10
     flooded
    0.10
     Flo
    0.09
     water
    0.09
     flash
    0.09
     overflow
    0.08
    Activations Density 0.024%

    No Known Activations