© 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. 35552
    Prev
    Next
    INDEX
    Explanations

    it has developed

    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
    ãĥ»ãĥ»ãĥ»\n\n
    -0.08
    306
    -0.08
     lai
    -0.08
     Emblem
    -0.07
     revel
    -0.07
    inate
    -0.07
    æĥ³åĪ°
    -0.07
    @nate
    -0.07
    517
    -0.07
     "(
    -0.07
    POSITIVE LOGITS
    rames
    0.10
    /stdc
    0.09
    rollers
    0.08
     overall
    0.08
    ÎĨ
    0.08
     OMIT
    0.08
    .TestCase
    0.08
     gazet
    0.08
    ýt
    0.08
    adele
    0.07
    Activations Density 0.617%

    No Known Activations