© 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. 28240
    Prev
    Next
    INDEX
    Explanations

    start output with specific phrase

    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
    631
    -0.12
     Schn
    -0.10
     fault
    -0.09
     Bain
    -0.09
    ëĭ¹
    -0.09
     Wings
    -0.08
    verbosity
    -0.08
     suce
    -0.08
    abeth
    -0.08
     “;âĢ¦
    -0.08
    POSITIVE LOGITS
    \xaa
    0.10
     word
    0.09
    YES
    0.08
    _YES
    0.08
    /aws
    0.08
    oves
    0.08
    ensi
    0.08
     pan
    0.08
    ì½
    0.08
     myst
    0.08
    Activations Density 0.030%

    No Known Activations