© 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. 31047
    Prev
    Next
    INDEX
    Explanations

    directory you want

    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
    æĹı
    -0.09
    riel
    -0.09
    663
    -0.09
    agine
    -0.09
    roller
    -0.09
     voc
    -0.08
     fled
    -0.08
    çŃĭ
    -0.08
    ä¼ı
    -0.08
    Playable
    -0.08
    POSITIVE LOGITS
     desired
    0.38
    desired
    0.29
    è¦ģ
    0.24
     Desired
    0.24
     wanted
    0.23
    æĥ³è¦ģ
    0.22
    欲
    0.21
     muá»ijn
    0.21
     desire
    0.18
    wanted
    0.17
    Activations Density 0.136%

    No Known Activations