© 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. 42769
    Prev
    Next
    INDEX
    Explanations

    simple, basic, new, current, ancient, default

    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
    VEC
    -0.09
    .Formatter
    -0.09
    ¦æĥħ
    -0.09
    alin
    -0.08
    láv
    -0.08
    /commons
    -0.08
    \Dependency
    -0.08
    :::|
    -0.08
    _readable
    -0.08
    erner
    -0.08
    POSITIVE LOGITS
    ibel
    0.09
     Hod
    0.08
     Griff
    0.08
    âīł
    0.08
    /load
    0.08
     Mobil
    0.08
     melod
    0.07
    rica
    0.07
     Willow
    0.07
     Licensed
    0.07
    Activations Density 0.265%

    No Known Activations