© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 39914
    Prev
    Next
    INDEX
    Explanations

    solution, system, platform, communities, study

    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
    creativecommons
    -0.09
    .INSTANCE
    -0.09
    izon
    -0.08
    uluk
    -0.08
     Lazar
    -0.08
     ï¼¼
    -0.08
    oenix
    -0.08
    :\n\n\n\n
    -0.08
    Combo
    -0.08
    473
    -0.07
    POSITIVE LOGITS
     usually
    0.09
     often
    0.09
    çļĦä¸Ģ
    0.09
    ofday
    0.08
     |\n
    0.08
     used
    0.08
    ¥
    0.08
     SYN
    0.08
    iteur
    0.08
     precursor
    0.07
    Activations Density 0.100%

    No Known Activations