© 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. 62349
    Prev
    Next
    INDEX
    Explanations

    significant degree or quantity

    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
     magnitude
    -0.11
    ugal
    -0.09
     cuff
    -0.09
     indispens
    -0.09
     менее
    -0.09
     gains
    -0.08
     techn
    -0.08
    plier
    -0.08
     erot
    -0.08
     unavoidable
    -0.08
    POSITIVE LOGITS
     greater
    0.20
    greater
    0.15
     greatest
    0.14
     great
    0.13
     higher
    0.13
     variable
    0.12
     considerable
    0.12
     high
    0.12
     decent
    0.11
    é«ĺãģĦ
    0.11
    Activations Density 0.121%

    No Known Activations