© 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. 19693
    Prev
    Next
    INDEX
    Explanations

    maintain order and behavior

    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
    å¾
    -0.10
    _NV
    -0.09
    mania
    -0.09
     truly
    -0.09
    é¸
    -0.09
    羣æŃ£
    -0.08
     autos
    -0.08
    å¾Ħ
    -0.08
    (always
    -0.08
    골
    -0.08
    POSITIVE LOGITS
     society
    0.13
     ourselves
    0.12
     shelter
    0.11
     our
    0.11
     we
    0.10
     exchange
    0.10
     human
    0.10
    èµĸ
    0.10
     goods
    0.09
     existence
    0.09
    Activations Density 0.206%

    No Known Activations