© 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. 35960
    Prev
    Next
    INDEX
    Explanations

    initial state or struggle

    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
     suddenly
    -0.12
     finally
    -0.12
     yet
    -0.12
     artık
    -0.11
    uddenly
    -0.10
     increasingly
    -0.10
     becoming
    -0.10
     dosud
    -0.10
    finally
    -0.10
    _BT
    -0.10
    POSITIVE LOGITS
    以为
    0.14
    åıªæĺ¯
    0.12
     glance
    0.12
     seemed
    0.11
    ono
    0.11
     just
    0.11
     thought
    0.11
    682
    0.11
     merely
    0.11
     simply
    0.10
    Activations Density 0.056%

    No Known Activations