© 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. 41730
    Prev
    Next
    INDEX
    Explanations

    in France or company names

    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
    194
    -0.16
    193
    -0.16
    195
    -0.13
    196
    -0.12
     Nazi
    -0.12
    Û±Û¹Û´
    -0.12
     radio
    -0.11
    192
    -0.11
     Radio
    -0.11
    ï¼ĪæĺŃåĴĮ
    -0.11
    POSITIVE LOGITS
    188
    0.44
    189
    0.43
    187
    0.38
     Victorian
    0.25
    186
    0.25
    190
    0.20
    185
    0.14
     Edison
    0.13
     Sherlock
    0.12
     anarchists
    0.12
    Activations Density 0.054%

    No Known Activations