© 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. 45327
    Prev
    Next
    INDEX
    Explanations

    crack egg and carefully pour

    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
     Fry
    -0.11
     dro
    -0.10
     chopped
    -0.10
     Sabb
    -0.10
    scratch
    -0.09
    walker
    -0.09
     पड
    -0.09
     paste
    -0.09
    mgr
    -0.09
    438
    -0.09
    POSITIVE LOGITS
     excess
    0.14
    èĴĤ
    0.12
     intact
    0.12
     shell
    0.11
     èĮ
    0.10
     Disc
    0.10
    å®
    0.10
     discard
    0.10
     opposite
    0.09
     stem
    0.09
    Activations Density 0.042%

    No Known Activations