© 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. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 64400
    Prev
    Next
    INDEX
    Explanations

    the river's flow

    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
     oceans
    -0.17
    æµ·
    -0.16
     ocean
    -0.14
     sea
    -0.14
     seas
    -0.13
     Ocean
    -0.12
     coastline
    -0.12
    Ocean
    -0.12
     æµ·
    -0.12
     seaside
    -0.12
    POSITIVE LOGITS
     river
    0.38
     River
    0.31
    River
    0.29
    river
    0.28
    æ²³
    0.27
     bank
    0.24
     Riverside
    0.22
     æ²³
    0.22
     banks
    0.22
     नद
    0.21
    Activations Density 0.088%

    No Known Activations