© 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
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 33597
    Prev
    Next
    INDEX
    Explanations

    too late, never too late

    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
     longevity
    -0.11
     GOODMAN
    -0.09
    ÅĻád
    -0.09
    776
    -0.09
    Callable
    -0.09
    681
    -0.08
     Goodman
    -0.08
    464
    -0.08
     Khan
    -0.08
     Pes
    -0.08
    POSITIVE LOGITS
     late
    0.44
    late
    0.34
     Late
    0.33
    Late
    0.31
    æĻļ
    0.27
     tarde
    0.24
     позд
    0.24
     pozdÄĽ
    0.18
    lates
    0.17
     damage
    0.17
    Activations Density 0.022%

    No Known Activations