© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37896
    Prev
    Next
    INDEX
    Explanations

    solidus and liquidus

    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
     Mund
    -0.10
    utive
    -0.09
     cock
    -0.09
     moll
    -0.09
    enberg
    -0.09
    ocos
    -0.08
     Ferr
    -0.08
     vá»ı
    -0.08
    osit
    -0.08
     mund
    -0.08
    POSITIVE LOGITS
     liquid
    0.29
     solid
    0.25
    liquid
    0.23
     Liquid
    0.22
    液
    0.21
     Solid
    0.20
     жид
    0.19
    solid
    0.19
    Solid
    0.19
    Liquid
    0.18
    Activations Density 0.064%

    No Known Activations