© 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. 1472
    Prev
    Next
    INDEX
    Explanations

    ice crystals or tiny particles

    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
     Marino
    -0.10
    enta
    -0.09
     Stephan
    -0.09
    erten
    -0.09
     conditions
    -0.09
    olley
    -0.09
    rees
    -0.09
     cons
    -0.09
     tre
    -0.09
    931
    -0.09
    POSITIVE LOGITS
     molecules
    0.27
     particles
    0.24
     tiny
    0.22
    olecules
    0.21
     cells
    0.19
    particles
    0.18
     molecule
    0.17
     dro
    0.17
     grains
    0.17
    Particles
    0.17
    Activations Density 0.155%

    No Known Activations