© 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 EvalsExportsinterp-engineNEWAPI 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. 69595
    Prev
    Next
    INDEX
    Explanations

    terms related to flood insurance and its regulation

    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
    alara
    -0.06
     heat
    -0.06
    izo
    -0.06
     Ober
    -0.06
    IAM
    -0.06
    opro
    -0.05
    acas
    -0.05
    ì¼ĵ
    -0.05
    gard
    -0.05
    isti
    -0.05
    POSITIVE LOGITS
     Flood
    0.09
    hur
    0.09
     flood
    0.08
     FEMA
    0.08
    Bounding
    0.07
     floods
    0.07
    bote
    0.07
    edException
    0.07
    gent
    0.07
     maps
    0.07
    Activations Density 0.003%

    No Known Activations