© 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. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 39171
    Prev
    Next
    INDEX
    Explanations

    waterfall flows over rocks

    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
    æµ®
    -0.11
    .scalablytyped
    -0.10
     Intr
    -0.10
    DSA
    -0.10
     sinking
    -0.10
     Peaks
    -0.09
     Slo
    -0.09
     Parade
    -0.09
    (interface
    -0.09
     Alf
    -0.09
    POSITIVE LOGITS
     falls
    0.27
     Falls
    0.24
     waterfall
    0.23
    falls
    0.22
    çĢ
    0.22
     rap
    0.21
     cascade
    0.21
     casc
    0.19
     Niagara
    0.18
     thác
    0.17
    Activations Density 0.034%

    No Known Activations