© 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. 46926
    Prev
    Next
    INDEX
    Explanations

    communicate benefits

    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
     suitability
    -0.09
    è¥
    -0.09
    uther
    -0.09
    olon
    -0.09
    VML
    -0.09
    linger
    -0.08
    usize
    -0.08
    ãng
    -0.08
     Soph
    -0.08
    aminer
    -0.08
    POSITIVE LOGITS
     addresses
    0.17
     fill
    0.16
    解åĨ³
    0.16
     solving
    0.16
     solve
    0.15
     addressing
    0.15
     Unique
    0.15
     fills
    0.14
     Fill
    0.14
     solution
    0.14
    Activations Density 0.096%

    No Known Activations