© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 28800
    Prev
    Next
    INDEX
    Explanations

    AI language model identification

    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
     Forces
    -0.09
     Rach
    -0.09
     tact
    -0.08
    ild
    -0.08
     Verm
    -0.08
     Modern
    -0.08
     ME
    -0.08
     Georg
    -0.08
     Prest
    -0.08
     Dob
    -0.08
    POSITIVE LOGITS
    mere
    0.11
    ¿ÃĤ
    0.10
    ::::/
    0.10
    åıªèĥ½
    0.10
    Inlining
    0.09
    Sharper
    0.09
     cannot
    0.09
    Ðĭ
    0.09
    IFF
    0.08
    ä¸įèĥ½
    0.08
    Activations Density 0.099%

    No Known Activations