© 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. 21601
    Prev
    Next
    INDEX
    Explanations

    type of blood cancer

    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
    æĺŃ
    -0.09
     fib
    -0.09
     Pap
    -0.09
    çĥŁ
    -0.09
     bottle
    -0.09
     Mush
    -0.09
     Chambers
    -0.08
     pap
    -0.08
     forensic
    -0.08
     lo
    -0.08
    POSITIVE LOGITS
     rel
    0.21
     mantle
    0.19
     Rit
    0.18
     rit
    0.17
     Hodg
    0.17
     NHL
    0.15
     CLL
    0.15
    mant
    0.15
     Rel
    0.15
     bend
    0.14
    Activations Density 0.026%

    No Known Activations