© 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. 3338
    Prev
    Next
    INDEX
    Explanations

    cardiovascular disease and conditions

    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
    ãĤĵãģ©
    -0.11
    .:.:
    -0.10
     Gallagher
    -0.10
     sto
    -0.09
    modo
    -0.09
     body
    -0.09
    íĴĪ
    -0.09
    oins
    -0.09
     pend
    -0.09
     wors
    -0.09
    POSITIVE LOGITS
     disease
    0.16
    çĸ¾
    0.13
     system
    0.13
    /card
    0.13
    ly
    0.12
     Disease
    0.11
    ular
    0.11
    lý
    0.11
     diseases
    0.11
    system
    0.11
    Activations Density 0.026%

    No Known Activations