© 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. 12850
    Prev
    Next
    INDEX
    Explanations

    water channel use

    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
    -0.12
     freshwater
    -0.11
     seas
    -0.11
     Seas
    -0.11
     fluids
    -0.10
     drip
    -0.10
     eth
    -0.10
     Hose
    -0.10
     Marine
    -0.09
    æµ·
    -0.09
    POSITIVE LOGITS
     turb
    0.19
     catch
    0.17
     trib
    0.17
     stream
    0.16
     recharge
    0.16
     rip
    0.16
     suspended
    0.15
     Stream
    0.15
     discharge
    0.15
     hydro
    0.15
    Activations Density 0.044%

    No Known Activations