© 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. 55132
    Prev
    Next
    INDEX
    Explanations

    instrument and variations

    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
    orc
    -0.09
    yar
    -0.09
    roit
    -0.09
     ​​
    -0.09
    /problems
    -0.09
    .jquery
    -0.08
    вей
    -0.08
    âĶģâĶģâĶģâĶģ
    -0.08
     rej
    -0.08
    NotificationCenter
    -0.08
    POSITIVE LOGITS
    arium
    0.24
    ality
    0.23
    ation
    0.21
    ations
    0.20
    ally
    0.20
    als
    0.17
    UMENT
    0.16
    alist
    0.15
    ATION
    0.14
    ational
    0.13
    Activations Density 0.018%

    No Known Activations