© 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. 17573
    Prev
    Next
    INDEX
    Explanations

    indirect or secondary source

    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
     isolated
    -0.10
    ãģ¾ãģ¾
    -0.09
     Verd
    -0.09
    arker
    -0.09
     matched
    -0.09
     naked
    -0.09
    earch
    -0.09
     iota
    -0.08
     explicitly
    -0.08
    åĮ¹
    -0.08
    POSITIVE LOGITS
     indirect
    0.71
     INDIRECT
    0.55
     indirectly
    0.51
    irect
    0.34
     vic
    0.26
     dolay
    0.25
     secondary
    0.24
     via
    0.21
    éĹ´
    0.21
    vic
    0.21
    Activations Density 0.152%

    No Known Activations