© 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. 3503
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers followed by comma

    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
     Alman
    -0.09
    KF
    -0.09
     intel
    -0.08
    /System
    -0.08
    lis
    -0.08
     Griff
    -0.08
     mne
    -0.08
    835
    -0.08
    baÅŁ
    -0.08
    erse
    -0.08
    POSITIVE LOGITS
    456
    0.09
    .sponge
    0.09
     sublist
    0.09
    (IDC
    0.09
    369
    0.08
    prit
    0.08
     Burr
    0.08
    htdocs
    0.08
    GuidId
    0.08
     Burk
    0.08
    Activations Density 0.026%

    No Known Activations