© 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. 29667
    Prev
    Next
    INDEX
    Explanations

    created once, before, ahead

    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
     preceded
    -0.12
     precedence
    -0.11
     Immediate
    -0.10
     preced
    -0.10
    bens
    -0.10
     firsthand
    -0.10
    ACES
    -0.09
     Lauderdale
    -0.09
    udd
    -0.08
    635
    -0.08
    POSITIVE LOGITS
     ahead
    0.54
     advance
    0.47
     Ahead
    0.44
    Ahead
    0.43
    ahead
    0.41
    advance
    0.38
    Advance
    0.37
     Advance
    0.37
    -ahead
    0.35
     prior
    0.29
    Activations Density 0.294%

    No Known Activations