© 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. 24313
    Prev
    Next
    INDEX
    Explanations

    requires or involves

    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
    indr
    -0.10
    rech
    -0.10
    ivent
    -0.09
    ::::
    -0.09
    ewan
    -0.09
     Cunningham
    -0.08
    lio
    -0.08
    fec
    -0.08
     NotSupportedException
    -0.08
    tsx
    -0.08
    POSITIVE LOGITS
     requires
    0.40
     require
    0.39
     Requires
    0.35
    requires
    0.34
    Requires
    0.30
     Require
    0.28
     requ
    0.26
    require
    0.26
     Äijòi
    0.25
    Require
    0.24
    Activations Density 0.143%

    No Known Activations