© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 29915
    Prev
    Next
    INDEX
    Explanations

    sea level rise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [email
    -0.11
     earthqu
    -0.10
     breakdown
    -0.10
     lakes
    -0.10
     riot
    -0.09
     Layers
    -0.09
     watershed
    -0.09
    èĮĤ
    -0.09
    è¡
    -0.09
     shelter
    -0.09
    POSITIVE LOGITS
     sea
    0.25
     tide
    0.20
     rise
    0.19
     rising
    0.18
     level
    0.18
     Rising
    0.17
     risen
    0.17
     tid
    0.17
    涨
    0.17
     Sea
    0.16
    Activations Density 0.030%

    No Known Activations