© 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. 33773
    Prev
    Next
    INDEX
    Explanations

    public defender representing defendant

    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
     sued
    -0.10
     judicial
    -0.10
     Fir
    -0.10
    thouse
    -0.09
     Cort
    -0.09
    æ³ķéĻ¢
    -0.09
     Lieutenant
    -0.09
     arbitration
    -0.09
    Ä°L
    -0.09
    ertia
    -0.08
    POSITIVE LOGITS
     defense
    0.22
     defence
    0.19
     argument
    0.19
     arguments
    0.18
     representing
    0.18
     counsel
    0.18
     representation
    0.18
     represented
    0.17
    defense
    0.16
     represent
    0.16
    Activations Density 0.021%

    No Known Activations