© 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. 61417
    Prev
    Next
    INDEX
    Explanations

    can say/see/guess

    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
     correctly
    -0.10
    owa
    -0.09
     rightly
    -0.09
    lesi
    -0.09
    ´
    -0.09
    éľĩ
    -0.08
     Hog
    -0.08
    èĥ½å¤Ł
    -0.08
     Fah
    -0.08
     benches
    -0.08
    POSITIVE LOGITS
     say
    0.20
    说
    0.15
     conclusion
    0.15
     safely
    0.15
     says
    0.14
     concluded
    0.14
     saying
    0.14
     sagen
    0.14
     said
    0.14
     safe
    0.13
    Activations Density 0.058%

    No Known Activations