© 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. 36084
    Prev
    Next
    INDEX
    Explanations

    not healthy or sustainable

    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
     simult
    -0.10
     Merr
    -0.09
    315
    -0.09
    ãĤ¤ãĥ¤
    -0.09
     hilar
    -0.09
    966
    -0.08
    697
    -0.08
    omers
    -0.08
    767
    -0.08
    argas
    -0.08
    POSITIVE LOGITS
     necessarily
    0.23
    ecessarily
    0.16
     automatically
    0.13
     completely
    0.12
     nor
    0.12
     обÑıзаÑĤелÑĮно
    0.12
     anymore
    0.11
    èĩ´
    0.11
     excuse
    0.10
     automatic
    0.10
    Activations Density 0.055%

    No Known Activations