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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14348
    Prev
    Next
    INDEX
    Explanations

    format codes and numbers

    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
     crossover
    -0.08
     Stre
    -0.08
    رÙĬÙĦ
    -0.07
    WithPath
    -0.07
    etti
    -0.07
    andard
    -0.07
    ppers
    -0.07
     Tüm
    -0.07
    isay
    -0.07
     sidebar
    -0.07
    POSITIVE LOGITS
     zero
    0.11
    28
    0.09
    23
    0.09
    21
    0.09
    13
    0.09
    14
    0.08
    12
    0.08
    22
    0.08
     ï¼ŀ
    0.08
    57
    0.08
    Activations Density 0.118%

    No Known Activations