© 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. 59582
    Prev
    Next
    INDEX
    Explanations

    glass and vetro

    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
     wre
    -0.11
     Nylon
    -0.10
    velle
    -0.09
     Metals
    -0.09
     Copper
    -0.09
    gid
    -0.09
     Gaines
    -0.09
    éĩijå±ŀ
    -0.09
    verb
    -0.09
     verb
    -0.09
    POSITIVE LOGITS
     glass
    0.46
     Glass
    0.43
    Glass
    0.38
    glass
    0.37
    çİ»çĴĥ
    0.32
     ÑģÑĤек
    0.27
     glasses
    0.25
     Glas
    0.24
     vit
    0.24
    erglass
    0.21
    Activations Density 0.025%

    No Known Activations