© 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. 43941
    Prev
    Next
    INDEX
    Explanations

    created by a comics

    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
     cellForRowAt
    -0.18
     Giuliani
    -0.13
     Axios
    -0.13
     Trump
    -0.12
    202
    -0.12
     macOS
    -0.11
     Ivanka
    -0.11
     Pelosi
    -0.11
     Pompeo
    -0.11
    Trump
    -0.10
    POSITIVE LOGITS
     Ebola
    0.36
     Obamacare
    0.22
     âĢª
    0.21
     Hollande
    0.19
     ISIL
    0.19
     Snowden
    0.18
    201
    0.17
     Obama
    0.16
    .fml
    0.16
     Benghazi
    0.16
    Activations Density 0.098%

    No Known Activations