© 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. 36060
    Prev
    Next
    INDEX
    Explanations

    just starting, was still

    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
     Simply
    -0.15
    Simply
    -0.12
     simplement
    -0.12
     simply
    -0.11
     rightful
    -0.09
     semp
    -0.09
    356
    -0.09
     próximo
    -0.08
    ubar
    -0.08
     pend
    -0.08
    POSITIVE LOGITS
     just
    0.55
    åĪļ
    0.51
    just
    0.42
    åīĽ
    0.41
     JUST
    0.38
     recently
    0.37
     vừa
    0.36
     newly
    0.35
     gerade
    0.32
    Just
    0.32
    Activations Density 0.168%

    No Known Activations