© 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. 25834
    Prev
    Next
    INDEX
    Explanations

    gradually becomes, were good, war changed

    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
    usan
    -0.10
     disappointed
    -0.09
     warned
    -0.09
    amps
    -0.09
     warning
    -0.09
     knowing
    -0.09
     bul
    -0.09
     Shr
    -0.09
    whel
    -0.09
    antic
    -0.09
    POSITIVE LOGITS
     slowly
    0.18
     chip
    0.14
    soft
    0.14
     dần
    0.14
     thaw
    0.13
     change
    0.13
     begin
    0.13
     softened
    0.13
     gradually
    0.13
     begins
    0.13
    Activations Density 0.039%

    No Known Activations