© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 37868
    Prev
    Next
    INDEX
    Explanations

    I cannot, don't have, must

    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
    GC
    -0.11
    ats
    -0.10
    field
    -0.10
    in
    -0.10
     Cas
    -0.10
    ion
    -0.10
    or
    -0.10
    ise
    -0.09
    2
    -0.09
     GC
    -0.09
    POSITIVE LOGITS
    ¶Į
    0.10
     unl
    0.10
    èīĩ
    0.10
    -------------</
    0.10
    ismet
    0.10
     cannot
    0.09
    awk
    0.09
    ÄįasÃŃ
    0.09
    awl
    0.09
     नह
    0.09
    Activations Density 0.076%

    No Known Activations