© 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. 59840
    Prev
    Next
    INDEX
    Explanations

    Project Integration Management process

    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
    _
    -0.12
    666
    -0.10
     pitch
    -0.10
    äº
    -0.10
    d
    -0.10
     unin
    -0.09
     Cup
    -0.09
     Rhodes
    -0.09
    /
    -0.09
    s
    -0.09
    POSITIVE LOGITS
     PM
    0.28
    PM
    0.20
     Project
    0.18
    (Project
    0.17
     pm
    0.17
    .pm
    0.16
    (pm
    0.15
    _PM
    0.14
    _pm
    0.14
    Project
    0.14
    Activations Density 0.044%

    No Known Activations