© 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. 26051
    Prev
    Next
    INDEX
    Explanations

    been adapted for functions

    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
     Nob
    -0.10
     Gib
    -0.10
     cont
    -0.09
     Cand
    -0.09
     sever
    -0.09
     gob
    -0.09
     clone
    -0.08
     proper
    -0.08
     Kaz
    -0.08
     Gut
    -0.08
    POSITIVE LOGITS
     evolution
    0.36
     Evolution
    0.32
     evolutionary
    0.29
     evolved
    0.25
     evolve
    0.22
    Ev
    0.22
    -ev
    0.20
     evolves
    0.19
     Adapt
    0.19
    ev
    0.18
    Activations Density 0.105%

    No Known Activations