© 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. 48799
    Prev
    Next
    INDEX
    Explanations

    dismiss or close or thinking

    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
     clearly
    -0.10
     Oliv
    -0.09
    opis
    -0.09
    Skipping
    -0.09
     jMenuItem
    -0.09
     Wiring
    -0.09
     suddenly
    -0.09
     slight
    -0.09
     realization
    -0.09
    Assertions
    -0.09
    POSITIVE LOGITS
     dismissed
    0.28
     dismiss
    0.25
    dismiss
    0.24
     dismissing
    0.24
     chalk
    0.23
     dismissal
    0.23
    Dismiss
    0.22
    -dismiss
    0.22
     thought
    0.20
    chalk
    0.19
    Activations Density 0.029%

    No Known Activations