© 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
    2. Llama3.3-70B-IT
    3. 50-RESID-POST-GF
    4. 35141
    Prev
    Next
    INDEX
    Explanations

    I cannot, I'm sorry, I must

    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
     guar
    -0.11
    arrant
    -0.10
     Richt
    -0.10
    echan
    -0.10
     invit
    -0.09
     Duch
    -0.09
    anal
    -0.09
     æ°
    -0.09
    invitation
    -0.08
    ayacak
    -0.08
    POSITIVE LOGITS
     cannot
    0.11
    radu
    0.10
     responsibility
    0.10
     ethical
    0.10
    åĬ
    0.10
     duty
    0.10
     obligation
    0.10
     moral
    0.10
    ummer
    0.09
     shar
    0.09
    Activations Density 0.151%

    No Known Activations