© 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. 41137
    Prev
    Next
    INDEX
    Explanations

    code operations in comments

    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
    Insensitive
    -0.10
     ########.
    -0.09
    .when
    -0.09
    xmax
    -0.09
     batt
    -0.09
    accumulate
    -0.09
    ilogy
    -0.08
    ivia
    -0.08
    Outputs
    -0.08
     interpol
    -0.08
    POSITIVE LOGITS
     define
    0.11
    å®ļä¹ī
    0.10
     Split
    0.10
    à¸Īร
    0.10
     print
    0.10
    åĪĽå»º
    0.10
     Define
    0.10
     split
    0.10
    转
    0.10
     convert
    0.09
    Activations Density 0.019%

    No Known Activations