© 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. 26714
    Prev
    Next
    INDEX
    Explanations

    1980s cultural and historical references

    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
    196
    -0.12
    Û±Û¹Û¶
    -0.11
     Manson
    -0.10
    ties
    -0.10
    nz
    -0.10
     Iso
    -0.10
    195
    -0.10
    Û±Û¹Ûµ
    -0.10
    200
    -0.09
    194
    -0.09
    POSITIVE LOGITS
     Reagan
    0.54
    198
    0.51
    Û±Û¹Û¸
    0.38
     Ronald
    0.29
     Thatcher
    0.28
     AIDS
    0.21
     cassette
    0.16
     Soviet
    0.15
     Madonna
    0.15
     yup
    0.15
    Activations Density 0.149%

    No Known Activations