© 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. 11914
    Prev
    Next
    INDEX
    Explanations

    despite initial efforts or odds

    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
     Highlands
    -0.11
    tract
    -0.10
    845
    -0.09
     Hopkins
    -0.09
    iken
    -0.09
    ÙĦÙħØ©
    -0.09
    635
    -0.08
     zwar
    -0.08
    ãĥ³ãĥī
    -0.08
    865
    -0.08
    POSITIVE LOGITS
     initial
    0.18
     protest
    0.18
     efforts
    0.17
     odds
    0.16
     everything
    0.15
     protests
    0.15
     initially
    0.14
    initial
    0.13
     Odds
    0.12
     Initial
    0.12
    Activations Density 0.012%

    No Known Activations