© 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. 20424
    Prev
    Next
    INDEX
    Explanations

    loved and all

    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
     ​​
    -0.09
    632
    -0.08
    now
    -0.08
    uye
    -0.08
     twig
    -0.08
     dood
    -0.08
     retrospective
    -0.08
     Parks
    -0.08
    ght
    -0.08
     increasingly
    -0.07
    POSITIVE LOGITS
    ноÑģи
    0.12
     loved
    0.12
     everyone
    0.11
     spends
    0.11
     spend
    0.11
     whenever
    0.11
     altijd
    0.11
     always
    0.11
     vždy
    0.10
     Spend
    0.10
    Activations Density 0.211%

    No Known Activations