© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 34968
    Prev
    Next
    INDEX
    Explanations

    historical years and periods

    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
    ----------</
    -0.09
     Hodg
    -0.09
    osc
    -0.09
    .***.***
    -0.09
     migrationBuilder
    -0.09
    ¹Ħ
    -0.08
    uzey
    -0.08
    iddi
    -0.08
    ï¾ĺ
    -0.08
    webkit
    -0.08
    POSITIVE LOGITS
    197
    0.29
    196
    0.29
    195
    0.29
    198
    0.28
    194
    0.27
    193
    0.27
    199
    0.26
    192
    0.24
    189
    0.21
    191
    0.21
    Activations Density 0.106%

    No Known Activations