© 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. 21264
    Prev
    Next
    INDEX
    Explanations

    are up-to-date and functional

    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
     trainable
    -0.10
    software
    -0.10
     Software
    -0.09
     ï¼ŀ
    -0.09
    ivot
    -0.08
    _nullable
    -0.08
     inf
    -0.08
     Holly
    -0.08
     assignable
    -0.08
     hil
    -0.08
    POSITIVE LOGITS
     mobile
    0.30
     Mobile
    0.26
    Mobile
    0.22
    mobile
    0.22
    -mobile
    0.22
    _mobile
    0.22
     моб
    0.20
    obile
    0.18
    /mobile
    0.18
    .mobile
    0.17
    Activations Density 0.060%

    No Known Activations