© 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. 30095
    Prev
    Next
    INDEX
    Explanations

    reduction and reduce

    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
    纪
    -0.10
     rud
    -0.10
    /read
    -0.09
    estruction
    -0.09
    rou
    -0.09
    æŀ¶
    -0.09
    icamente
    -0.09
    adder
    -0.09
    eliness
    -0.09
     Karlov
    -0.09
    POSITIVE LOGITS
    ible
    0.16
     thiá»ĥu
    0.15
    dish
    0.14
    .Red
    0.11
    dest
    0.10
    à¸ĺ
    0.10
    ial
    0.10
     equivalents
    0.10
    ase
    0.10
    alist
    0.10
    Activations Density 0.018%

    No Known Activations