© 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. 35159
    Prev
    Next
    INDEX
    Explanations

    constant and unchanging states

    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
    _consts
    -0.09
    amy
    -0.09
    946
    -0.09
    istrovstvÃŃ
    -0.09
    AMY
    -0.09
    unas
    -0.09
    fulness
    -0.09
    ï¸ı
    -0.09
    agg
    -0.09
    irsch
    -0.09
    POSITIVE LOGITS
    antly
    0.14
    ellation
    0.14
    ine
    0.14
    aneous
    0.13
    ipation
    0.13
    ipated
    0.12
    inos
    0.12
    ijn
    0.12
    aneously
    0.11
    emente
    0.11
    Activations Density 0.013%

    No Known Activations