© 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. 44574
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

    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
    455
    -0.09
    adesh
    -0.08
    348
    -0.08
    927
    -0.08
     exper
    -0.08
    âī§
    -0.08
    erokee
    -0.07
    /Footer
    -0.07
    coli
    -0.07
    ura
    -0.07
    POSITIVE LOGITS
     aforementioned
    0.10
    ogl
    0.08
    rosse
    0.08
     Sav
    0.08
     //~
    0.08
    _executor
    0.08
    //{{
    0.07
     ‘;
    0.07
    qs
    0.07
     contentValues
    0.07
    Activations Density 0.101%

    No Known Activations