© 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. 21971
    Prev
    Next
    INDEX
    Explanations

    nosebleeds or suspect illness

    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
    657
    -0.09
    YPE
    -0.09
    PPER
    -0.09
     Daw
    -0.09
    ipes
    -0.09
     cref
    -0.09
     prt
    -0.08
     sanct
    -0.08
     vas
    -0.08
    å¤ļå°ij
    -0.08
    POSITIVE LOGITS
     fever
    0.15
     Fever
    0.13
     wor
    0.12
     severe
    0.12
     lasts
    0.11
     signs
    0.11
     difficulty
    0.10
     Rowe
    0.10
     accompagn
    0.10
     lasted
    0.10
    Activations Density 0.017%

    No Known Activations