© 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. 54904
    Prev
    Next
    INDEX
    Explanations

    90 followed by units or characters

    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
    orrow
    -0.10
    tures
    -0.10
     distr
    -0.09
     pencil
    -0.09
     herr
    -0.09
    ÑĢаÑĩ
    -0.09
    wd
    -0.09
     stiff
    -0.09
    INDER
    -0.08
     Äijêm
    -0.08
    POSITIVE LOGITS
    alim
    0.11
    .scalablytyped
    0.10
    entr
    0.10
    mez
    0.10
    breaker
    0.10
    年代
    0.09
    unik
    0.09
    90
    0.09
    ably
    0.09
    ries
    0.09
    Activations Density 0.050%

    No Known Activations