© 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. 28880
    Prev
    Next
    INDEX
    Explanations

    special character sequences

    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
    OAD
    -0.09
    alm
    -0.09
    #
    -0.08
    chartInstance
    -0.08
    .SEVER
    -0.08
     pur
    -0.08
     Sle
    -0.08
    AZY
    -0.08
     PURE
    -0.08
    eni
    -0.08
    POSITIVE LOGITS
    ï¸ı
    0.16
    ï¸
    0.10
    quez
    0.08
    彡
    0.08
    ida
    0.08
    Opaque
    0.08
     Kirk
    0.08
    ãĥ¶æľĪ
    0.08
    nbsp
    0.08
    imos
    0.08
    Activations Density 0.036%

    No Known Activations