© 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. 58275
    Prev
    Next
    INDEX
    Explanations

    describe to me

    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
    semble
    -0.11
     Ung
    -0.09
    stead
    -0.08
     TMPro
    -0.08
    acle
    -0.08
    leep
    -0.08
    advert
    -0.08
    ché
    -0.08
    vu
    -0.07
    gili
    -0.07
    POSITIVE LOGITS
    slashes
    0.10
    jem
    0.10
    AndGet
    0.09
     nÃło
    0.09
    num
    0.08
    asel
    0.08
    _each
    0.08
    zin
    0.08
    elerik
    0.08
     Wes
    0.08
    Activations Density 0.187%

    No Known Activations