© 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. 13956
    Prev
    Next
    INDEX
    Explanations

    next or then transitions

    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
    ometr
    -0.10
    Immediately
    -0.09
    otti
    -0.08
     replay
    -0.08
    ãĤıãģļ
    -0.08
    Immediate
    -0.08
     Overnight
    -0.08
     váºŃy
    -0.08
    owy
    -0.08
    882
    -0.08
    POSITIVE LOGITS
     next
    0.28
     Next
    0.27
    Next
    0.23
    next
    0.19
     then
    0.19
    _next
    0.18
     Then
    0.18
     näch
    0.17
    -next
    0.17
     NEXT
    0.17
    Activations Density 0.026%

    No Known Activations