© 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. 30986
    Prev
    Next
    INDEX
    Explanations

    assistant, we, avoid

    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
     your
    -0.14
     you
    -0.14
    ä½łçļĦ
    -0.13
     YOU
    -0.13
     ä½ł
    -0.13
    ä½ł
    -0.13
     sorry
    -0.12
    sorry
    -0.12
    _you
    -0.12
    Ĥ¨
    -0.12
    POSITIVE LOGITS
     wonder
    0.19
     wonders
    0.16
     Wonder
    0.14
     maybe
    0.13
    Wonder
    0.13
     why
    0.11
    å¸ĮæľĽ
    0.11
    odge
    0.11
     Maybe
    0.11
     myself
    0.10
    Activations Density 0.079%

    No Known Activations