© 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. 29998
    Prev
    Next
    INDEX
    Explanations

    math, industry, physics, code, writing

    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
    imits
    -0.08
    esub
    -0.08
    -------------</
    -0.08
    .UIManager
    -0.08
    .cljs
    -0.07
    951
    -0.07
    надлеж
    -0.07
    avad
    -0.07
    \Dependency
    -0.07
     uninitialized
    -0.07
    POSITIVE LOGITS
     favor
    0.07
    .in
    0.07
     Reb
    0.07
     prof
    0.07
     FIR
    0.07
     eyeb
    0.07
     misd
    0.07
     ``
    0.07
    chants
    0.06
     Wade
    0.06
    Activations Density 1.198%

    No Known Activations