© 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. 35366
    Prev
    Next
    INDEX
    Explanations

    lead to hurt or discrimination

    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
     Interr
    -0.10
     irrit
    -0.10
    chn
    -0.09
     factor
    -0.09
     ãĢī
    -0.09
     nature
    -0.09
     brutal
    -0.09
    ause
    -0.09
     lá»Ĺi
    -0.09
     temper
    -0.09
    POSITIVE LOGITS
     harm
    0.16
     further
    0.12
     hurt
    0.12
     serious
    0.12
     dangerous
    0.11
     problems
    0.11
     conclusions
    0.11
     consequences
    0.11
     exploitation
    0.11
     Harm
    0.10
    Activations Density 0.042%

    No Known Activations