© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 35342
    Prev
    Next
    INDEX
    Explanations

    user `firstName` check

    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
     ull
    -0.09
     hier
    -0.08
     koc
    -0.08
     Brew
    -0.08
     Parsons
    -0.08
    _likelihood
    -0.08
    659
    -0.08
     Fle
    -0.08
     CCT
    -0.08
    787
    -0.08
    POSITIVE LOGITS
     Sokol
    0.10
    <|begin_of_text|>
    0.09
    ezi
    0.08
    मर
    0.08
    _GEN
    0.08
    \uff
    0.08
    ottie
    0.08
    EMPLARY
    0.08
    .valueOf
    0.08
     Fo
    0.08
    Activations Density 0.081%

    No Known Activations