© 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. 17216
    Prev
    Next
    INDEX
    Explanations

    has since grown

    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
     unm
    -0.11
    ibi
    -0.10
    /*č\n
    -0.10
     increasingly
    -0.09
     sour
    -0.09
     recently
    -0.09
    oret
    -0.09
    *=*=
    -0.09
    æľĢè¿ij
    -0.08
     TBD
    -0.08
    POSITIVE LOGITS
     initially
    0.29
     initial
    0.25
    initial
    0.24
    æľĢåĪĿ
    0.19
     Initially
    0.19
     originally
    0.19
     early
    0.19
     Initial
    0.19
     inicial
    0.18
     quickly
    0.18
    Activations Density 0.109%

    No Known Activations