© 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. 2121
    Prev
    Next
    INDEX
    Explanations

    still

    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
     increasingly
    -0.10
    reon
    -0.09
    uros
    -0.09
    asters
    -0.09
     abl
    -0.08
     became
    -0.08
     chẳng
    -0.08
    PMC
    -0.08
    à¹Ģลย
    -0.08
     ever
    -0.08
    POSITIVE LOGITS
     still
    0.59
    still
    0.49
    ãģ¾ãģł
    0.44
     ainda
    0.43
     masih
    0.42
     ìķĦì§ģ
    0.42
    Still
    0.42
     Still
    0.41
     ancora
    0.41
     henüz
    0.41
    Activations Density 0.161%

    No Known Activations