© 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. 36544
    Prev
    Next
    INDEX
    Explanations

    evenly distributed

    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
    upplier
    -0.10
     pon
    -0.09
    ITE
    -0.09
     asymmetric
    -0.09
    IEL
    -0.09
    rzy
    -0.09
    IVA
    -0.09
     counterparts
    -0.08
    iene
    -0.08
    arching
    -0.08
    POSITIVE LOGITS
     equal
    0.54
     equally
    0.45
     Equal
    0.44
    equal
    0.43
     uniform
    0.42
     ÑĢав
    0.42
    åĿĩ
    0.41
    Equal
    0.41
     igual
    0.39
     equ
    0.36
    Activations Density 0.190%

    No Known Activations