© 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. 32996
    Prev
    Next
    INDEX
    Explanations

    stem cell transplantation for cancers

    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
     åĺ
    -0.11
     Sug
    -0.10
     Heller
    -0.09
     Rapids
    -0.09
     hypert
    -0.09
    çī
    -0.09
     dyst
    -0.09
     Nec
    -0.09
    Verb
    -0.09
    olec
    -0.09
    POSITIVE LOGITS
     pom
    0.16
     Pom
    0.14
     bone
    0.14
    骨
    0.13
     rel
    0.13
     Wald
    0.13
     len
    0.13
     plasma
    0.13
    é«
    0.12
     MM
    0.12
    Activations Density 0.014%

    No Known Activations