© 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. 45158
    Prev
    Next
    INDEX
    Explanations

    breeze to rust, glow to fills, mind to a

    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
     eman
    -0.10
     foc
    -0.09
     get
    -0.09
     look
    -0.09
    erna
    -0.09
     day
    -0.08
    ippet
    -0.08
     kill
    -0.08
     sic
    -0.08
    çĽ
    -0.08
    POSITIVE LOGITS
     birth
    0.13
     births
    0.10
    birth
    0.10
    heimer
    0.10
    jar
    0.09
     Claus
    0.09
    blr
    0.09
     realpath
    0.09
    tres
    0.08
     Birth
    0.08
    Activations Density 0.138%

    No Known Activations