© 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. 38874
    Prev
    Next
    INDEX
    Explanations

    extraction process

    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
     purified
    -0.13
     Dol
    -0.12
     dol
    -0.11
    peg
    -0.10
     excess
    -0.10
     Fritz
    -0.10
     sut
    -0.10
    dol
    -0.09
     Leap
    -0.09
     noreferrer
    -0.09
    POSITIVE LOGITS
    æıIJ
    0.18
     extraction
    0.18
    _extraction
    0.16
     extract
    0.15
     crushing
    0.14
     Sox
    0.14
     Extraction
    0.14
     solvent
    0.13
     extracting
    0.13
     extractor
    0.13
    Activations Density 0.039%

    No Known Activations