© 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. 36942
    Prev
    Next
    INDEX
    Explanations

    form opinions and bonds

    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
    rax
    -0.09
    tings
    -0.09
    615
    -0.09
    iola
    -0.09
    314
    -0.09
    UpDown
    -0.09
    lok
    -0.09
    ibri
    -0.09
     inn
    -0.08
    steder
    -0.08
    POSITIVE LOGITS
     bonds
    0.18
    ulates
    0.17
     opinion
    0.15
     opinions
    0.15
     bond
    0.15
    ulating
    0.14
     opin
    0.14
     lasting
    0.14
     Opinion
    0.13
    lasting
    0.12
    Activations Density 0.048%

    No Known Activations