© 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. 43506
    Prev
    Next
    INDEX
    Explanations

    we will discuss

    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
    uche
    -0.09
    à¹ģà¸Ļ
    -0.09
     ken
    -0.09
    ัส
    -0.08
    adiens
    -0.08
    ï¼ľ
    -0.08
     Ansi
    -0.08
     replay
    -0.08
     famed
    -0.08
    erule
    -0.08
    POSITIVE LOGITS
     will
    0.21
     sẽ
    0.18
    aremos
    0.17
    ’;ll
    0.16
     shall
    0.16
    'll
    0.15
     akan
    0.15
    will
    0.13
     бÑĥдеÑĤ
    0.12
    å°Ĩ
    0.12
    Activations Density 0.021%

    No Known Activations