© 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. 37535
    Prev
    Next
    INDEX
    Explanations

    change from once to now

    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
    /Dk
    -0.09
    _tid
    -0.09
    <|begin_of_text|>
    -0.08
    ãĢķ
    -0.08
    /on
    -0.08
    landa
    -0.08
     丶
    -0.08
    ÄįasÃŃ
    -0.08
    391
    -0.08
     zaten
    -0.08
    POSITIVE LOGITS
     now
    0.34
    now
    0.25
     ÑĤепеÑĢÑĮ
    0.22
     Now
    0.22
     ahora
    0.21
    ï¼Įçİ°åľ¨
    0.20
    Now
    0.18
     suddenly
    0.18
     became
    0.18
    -now
    0.18
    Activations Density 0.049%

    No Known Activations