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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44365
    Prev
    Next
    INDEX
    Explanations

    corruption and bribery

    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
    LTR
    -0.09
     fores
    -0.09
    484
    -0.09
    ãĢķ
    -0.09
    ugi
    -0.09
    anka
    -0.09
     hoax
    -0.09
    è´£
    -0.09
    _warnings
    -0.09
    pun
    -0.09
    POSITIVE LOGITS
     corruption
    0.43
     corrupt
    0.40
     Corruption
    0.36
     bri
    0.35
     corrupted
    0.31
    èħIJ
    0.31
     graft
    0.30
     Bri
    0.29
     brib
    0.28
     bribery
    0.27
    Activations Density 0.073%

    No Known Activations