© 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. 56540
    Prev
    Next
    INDEX
    Explanations

    and I / morning , / had an / may try

    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
     currently
    -0.10
     éĩ
    -0.09
    inan
    -0.09
    ston
    -0.09
    çĽĬ
    -0.08
    727
    -0.08
     fortunate
    -0.08
     unlikely
    -0.08
    _legend
    -0.08
     noop
    -0.08
    POSITIVE LOGITS
    以为
    0.27
     thought
    0.23
     hopes
    0.19
     initially
    0.18
     hoped
    0.18
     seemed
    0.17
     Thought
    0.17
     promising
    0.16
    thought
    0.16
     hopeful
    0.16
    Activations Density 0.219%

    No Known Activations