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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 14131
    Prev
    Next
    INDEX
    Explanations

    if, ignore, assuming

    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
     judging
    -0.11
    recall
    -0.09
    Äħd
    -0.09
     Mug
    -0.08
    ogan
    -0.08
    ye
    -0.08
    implicitly
    -0.08
     bursting
    -0.08
     Alf
    -0.08
     multiplication
    -0.08
    POSITIVE LOGITS
    忽
    0.21
     Ign
    0.21
    ign
    0.18
     discount
    0.18
     if
    0.17
    Ignoring
    0.16
    åģĩ
    0.16
    discount
    0.15
     ignore
    0.15
     ignoring
    0.15
    Activations Density 0.300%

    No Known Activations