© 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. 51442
    Prev
    Next
    INDEX
    Explanations

    for larger, to improve

    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
     Zus
    -0.10
     direct
    -0.10
     cust
    -0.10
    lett
    -0.09
     Difference
    -0.09
    enz
    -0.09
    extr
    -0.09
    prim
    -0.09
     flam
    -0.09
    388
    -0.08
    POSITIVE LOGITS
     divers
    0.23
     diversity
    0.22
     spreading
    0.20
     Diversity
    0.19
     spread
    0.18
     Spread
    0.16
     dil
    0.16
     redundancy
    0.14
    Spread
    0.14
    iversity
    0.14
    Activations Density 0.067%

    No Known Activations