© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 17098
    Prev
    Next
    INDEX
    Explanations

    references to flood insurance and its related concepts

    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
    patches
    -0.08
     takson
    -0.07
    .Debugger
    -0.07
    .showMessage
    -0.07
    /Instruction
    -0.07
    çĸĹ
    -0.07
    ItemImage
    -0.07
    .getField
    -0.06
    ntax
    -0.06
    onest
    -0.06
    POSITIVE LOGITS
     flood
    0.13
     Flood
    0.11
     flooding
    0.10
     inund
    0.10
     floods
    0.09
     vulnerability
    0.09
     FEMA
    0.08
    æ´ª
    0.07
     hazard
    0.07
     risk
    0.07
    Activations Density 0.076%

    No Known Activations