© 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
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44138
    Prev
    Next
    INDEX
    Explanations

    hydro- prefixed words

    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
    ut
    -0.10
    wand
    -0.09
    page
    -0.09
     Marl
    -0.09
    lets
    -0.09
     thang
    -0.09
    wan
    -0.09
    por
    -0.08
     Kle
    -0.08
    adu
    -0.08
    POSITIVE LOGITS
    ly
    0.15
    xy
    0.14
    dynamic
    0.13
    pon
    0.12
    static
    0.11
    electric
    0.11
    x
    0.11
     Hamm
    0.11
    apat
    0.11
    antically
    0.10
    Activations Density 0.020%

    No Known Activations