© 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. 35758
    Prev
    Next
    INDEX
    Explanations

    instruction completion

    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
    ye
    -0.10
    ienza
    -0.10
     Entr
    -0.09
     Cathy
    -0.09
     Brook
    -0.09
     meas
    -0.09
    yr
    -0.08
     returned
    -0.08
     entr
    -0.08
    .scalablytyped
    -0.08
    POSITIVE LOGITS
     Completion
    0.09
    icum
    0.09
     completion
    0.09
    anka
    0.09
    _subtype
    0.09
    ovie
    0.09
    pson
    0.09
    udden
    0.08
    684
    0.08
    ç«
    0.08
    Activations Density 0.008%

    No Known Activations