© 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. 58309
    Prev
    Next
    INDEX
    Explanations

    donc pas / you can

    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
     cant
    -0.17
     Unable
    -0.14
     Cannot
    -0.13
    åıªèĥ½
    -0.13
     inability
    -0.13
     못
    -0.12
    Unable
    -0.12
    unable
    -0.12
    Impossible
    -0.12
     Canton
    -0.11
    POSITIVE LOGITS
     nemus
    0.34
     unnecessary
    0.31
     need
    0.29
    need
    0.24
     Need
    0.22
     doesn
    0.22
    ä¸įè¦ģ
    0.22
     no
    0.22
     необ
    0.21
     don
    0.20
    Activations Density 0.164%

    No Known Activations