© 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. 21630
    Prev
    Next
    INDEX
    Explanations

    removal and draining

    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
     dissolved
    -0.11
     disin
    -0.10
     severed
    -0.10
     sever
    -0.10
     thaw
    -0.10
     demol
    -0.09
     Clips
    -0.09
     Tear
    -0.09
     suspended
    -0.09
    åī²
    -0.09
    POSITIVE LOGITS
     removed
    0.24
     removal
    0.21
     remove
    0.20
     Removed
    0.18
     neutral
    0.17
     entfer
    0.17
     harmless
    0.17
    removed
    0.17
     harm
    0.17
     removing
    0.16
    Activations Density 0.048%

    No Known Activations