© 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. 41317
    Prev
    Next
    INDEX
    Explanations

    the first is

    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
    inspace
    -0.10
    ils
    -0.10
    éģ©
    -0.09
     deb
    -0.09
     Benton
    -0.09
    lse
    -0.08
     Guar
    -0.08
     Bras
    -0.08
     bore
    -0.08
     Mang
    -0.08
    POSITIVE LOGITS
     argument
    0.12
     passed
    0.11
    argument
    0.11
     Passed
    0.10
    411
    0.10
    aley
    0.10
    ä¸įèĥ½ä¸ºç©º
    0.10
    å¿ħé¡»
    0.10
    oby
    0.10
    Defaults
    0.09
    Activations Density 0.063%

    No Known Activations