© 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. 24107
    Prev
    Next
    INDEX
    Explanations

    special markers

    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
     caller
    -0.12
     clothes
    -0.10
    Delegate
    -0.09
    888
    -0.09
     tong
    -0.09
     delegate
    -0.09
     reb
    -0.09
    udi
    -0.09
     Clothes
    -0.09
    Ãķ
    -0.09
    POSITIVE LOGITS
     annotation
    0.18
    \Annotation
    0.18
    annotation
    0.18
    .annotation
    0.17
     ann
    0.17
    注
    0.16
    饰
    0.16
    anno
    0.15
    .annotations
    0.14
     decorator
    0.14
    Activations Density 0.089%

    No Known Activations