© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43974
    Prev
    Next
    INDEX
    Explanations

    subjective, speculative, volatile

    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
     requestOptions
    -0.08
    .cn
    -0.08
     savage
    -0.08
    /reference
    -0.08
    grim
    -0.08
    ê·Ģ
    -0.08
    imits
    -0.08
    ully
    -0.08
    <quote
    -0.07
    vt
    -0.07
    POSITIVE LOGITS
     nature
    0.18
     affair
    0.14
    nature
    0.13
     due
    0.13
     Nature
    0.11
     affairs
    0.11
    due
    0.11
    ä¸Ķ
    0.10
     enough
    0.10
     because
    0.10
    Activations Density 0.066%

    No Known Activations