© 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. 16626
    Prev
    Next
    INDEX
    Explanations

    progress over time

    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
    âī¦
    -0.10
    é±
    -0.09
    304
    -0.09
    leur
    -0.09
     clin
    -0.09
     elect
    -0.09
     distant
    -0.08
     Vance
    -0.08
     Bruno
    -0.08
    leurs
    -0.08
    POSITIVE LOGITS
     wore
    0.20
     continue
    0.17
     continues
    0.16
     wears
    0.16
     continued
    0.15
     progressed
    0.15
     progresses
    0.15
     advanced
    0.15
    progress
    0.14
     progress
    0.14
    Activations Density 0.010%

    No Known Activations