© 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. 41347
    Prev
    Next
    INDEX
    Explanations

    query/answer structure

    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
    emens
    -0.09
    UME
    -0.09
    rips
    -0.08
    659
    -0.08
     Lou
    -0.08
    haps
    -0.08
     Bronze
    -0.08
    apis
    -0.08
     tune
    -0.08
    tsky
    -0.08
    POSITIVE LOGITS
    åĥį
    0.09
    IIIK
    0.09
     Dexter
    0.09
    itional
    0.09
     Shim
    0.09
    que
    0.09
    <|begin_of_text|>
    0.08
     Wick
    0.08
    CONT
    0.08
    æī¶
    0.08
    Activations Density 0.007%

    No Known Activations