© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 22389
    Prev
    Next
    INDEX
    Explanations

    layer or physical barrier

    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
     coated
    -0.09
     Inside
    -0.09
    ëij¥
    -0.09
     bundled
    -0.09
    _inside
    -0.09
     cụ
    -0.08
     pore
    -0.08
    ARRANT
    -0.08
     pouch
    -0.08
     Blocked
    -0.08
    POSITIVE LOGITS
     layer
    0.48
    layer
    0.33
     layers
    0.32
    å±Ĥ
    0.32
     Ñģлой
    0.31
     Layer
    0.30
    層
    0.29
    Layer
    0.28
    _layer
    0.28
     lỼp
    0.25
    Activations Density 0.095%

    No Known Activations