© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 8676
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    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
     Seven
    -0.11
    3
    -0.11
     Seventh
    -0.11
     seven
    -0.10
    7
    -0.10
    07
    -0.09
     seventh
    -0.09
     ​​
    -0.09
     c
    -0.08
     tradition
    -0.08
    POSITIVE LOGITS
    ï¼ijï¼IJ
    0.18
    10
    0.17
     tenth
    0.16
    Û±Û°
    0.14
    åįģ
    0.14
     деÑģÑıÑĤ
    0.11
     деÑģÑı
    0.11
     दस
    0.10
     Ø£ÙĥتÙĪبر
    0.10
    .jupiter
    0.10
    Activations Density 0.025%

    No Known Activations