© 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. 24394
    Prev
    Next
    INDEX
    Explanations

    statements of duty and importance

    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
     ï¼ŀ
    -0.11
    APPER
    -0.09
     insult
    -0.09
     Hein
    -0.09
    169
    -0.09
    èĮ
    -0.09
    .rules
    -0.08
    451
    -0.08
    otal
    -0.08
    .broadcast
    -0.08
    POSITIVE LOGITS
     unl
    0.11
    ãĤĩ
    0.11
     NEVER
    0.10
     never
    0.09
     better
    0.09
     wholes
    0.09
     -*-č\n
    0.09
     Never
    0.09
    dent
    0.09
     taught
    0.08
    Activations Density 0.079%

    No Known Activations