© 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. 57557
    Prev
    Next
    INDEX
    Explanations

    special tokens

    np_acts-logits-general · gemini-2.5-flash-lite

    end-of-turn separator tokens marking the boundary between messages.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     informal
    -0.09
    uner
    -0.09
    éĢĶ
    -0.08
    Tanggal
    -0.08
    .volley
    -0.08
    reta
    -0.08
    alus
    -0.08
    ils
    -0.08
    tah
    -0.08
    _flutter
    -0.08
    POSITIVE LOGITS
    ãĥĭãĤ¢
    0.10
     Jal
    0.08
     republik
    0.08
     oblig
    0.08
    ubbles
    0.08
    ï½ŀï½ŀ
    0.08
    uest
    0.08
     Herz
    0.08
    555
    0.08
    ëįĶëĭĪ
    0.08
    Activations Density 0.396%

    No Known Activations