© 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. 168
    Prev
    Next
    INDEX
    Explanations

    past states

    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
    缮åīį
    -0.14
     currently
    -0.12
    äºĨ
    -0.11
     increasingly
    -0.10
     soon
    -0.10
    æĪIJäºĨ
    -0.10
     unchanged
    -0.10
    æľĢè¿ij
    -0.09
    ãģķãĤĮãģ¦ãģĦãĤĭ
    -0.09
    rak
    -0.09
    POSITIVE LOGITS
    (before
    0.19
    .Now
    0.17
     before
    0.15
    -now
    0.15
    æĽ¾
    0.14
    à¹Ģà¸Ħย
    0.14
    .Today
    0.13
    ï¼Įçİ°åľ¨
    0.13
     yoktu
    0.13
     was
    0.13
    Activations Density 0.147%

    No Known Activations