© 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. 33810
    Prev
    Next
    INDEX
    Explanations

    following steps or solutions

    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
    Verse
    -0.10
     Gard
    -0.10
    WithMany
    -0.09
    zer
    -0.09
    Parms
    -0.08
     âĸ³
    -0.08
    owi
    -0.08
    uye
    -0.08
    yped
    -0.08
    ibr
    -0.08
    POSITIVE LOGITS
     steps
    0.22
     suggestions
    0.19
     solutions
    0.18
     above
    0.18
     options
    0.17
     suggested
    0.16
    steps
    0.16
     Steps
    0.16
     option
    0.15
     Solutions
    0.15
    Activations Density 0.015%

    No Known Activations