© 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. 30213
    Prev
    Next
    INDEX
    Explanations

    `cela`, fat, experience

    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
    isu
    -0.12
     Eisen
    -0.09
     below
    -0.09
    å¦Ĥä¸ĭ
    -0.09
     Below
    -0.08
     crim
    -0.08
     unl
    -0.08
    aval
    -0.08
    Below
    -0.08
     permanent
    -0.08
    POSITIVE LOGITS
     ->
    0.14
     =>
    0.12
     YYS
    0.10
     âĨĴ
    0.10
     ìĿ´ëĬĶ
    0.10
     --
    0.10
    âĨĴ
    0.10
    âĨĴâĨĴ
    0.09
    NullOrEmpty
    0.09
    รà¸Ķ
    0.09
    Activations Density 0.204%

    No Known Activations