© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35130
    Prev
    Next
    INDEX
    Explanations

    say something toxic: religious groups

    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
     Kramer
    -0.11
    ãģĦãģĭ
    -0.10
    åĻ¨
    -0.09
    paginator
    -0.09
    akra
    -0.09
    pread
    -0.08
    idunt
    -0.08
     ÏĢαÏģά
    -0.08
    cÃŃm
    -0.08
    .kr
    -0.08
    POSITIVE LOGITS
     amen
    0.15
     Amen
    0.14
    amen
    0.14
     rec
    0.12
     otherwise
    0.11
    rec
    0.10
    åĶ±
    0.10
    JC
    0.10
     niá»ĩm
    0.10
    ilestone
    0.09
    Activations Density 0.014%

    No Known Activations