© 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. 59177
    Prev
    Next
    INDEX
    Explanations

    pre-training

    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
     Tib
    -0.08
    =$('#
    -0.08
    &&&&
    -0.08
    oli
    -0.07
    handleSubmit
    -0.07
    imen
    -0.07
    ÙĪÙĤت
    -0.07
    ernaut
    -0.07
    atic
    -0.07
    heimer
    -0.07
    POSITIVE LOGITS
    Uvs
    0.10
    езÑĥлÑĮÑĤ
    0.10
     aforementioned
    0.10
    Â
    0.09
    ï¼ģãĢį\n\n
    0.09
     Nová
    0.08
    ẵ
    0.08
    dÃŃ
    0.08
    иÑĤÑĥа
    0.08
     [=
    0.08
    Activations Density 0.171%

    No Known Activations