© 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. 18032
    Prev
    Next
    INDEX
    Explanations

    serious consequences

    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
    ante
    -0.10
    igy
    -0.10
    osta
    -0.09
    /archive
    -0.09
     sprawling
    -0.09
    ÏĥÏĦε
    -0.09
     noop
    -0.09
    atan
    -0.08
    asco
    -0.08
     Harm
    -0.08
    POSITIVE LOGITS
     extreme
    0.43
     worst
    0.36
     Extreme
    0.32
    Extreme
    0.32
     severe
    0.28
     Worst
    0.25
    æŀģ
    0.25
     extremes
    0.24
     worse
    0.23
    極
    0.23
    Activations Density 0.027%

    No Known Activations