© 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. 41840
    Prev
    Next
    INDEX
    Explanations

    involves several steps

    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
    ÅĻÃŃz
    -0.10
    anker
    -0.09
    ÙĦÙĬÙĩ
    -0.09
    Ø´ÙħاÙĦÛĮ
    -0.09
     Stable
    -0.09
    IIIK
    -0.08
    ัสà¸Ķ
    -0.08
     Cunning
    -0.08
    -Clause
    -0.08
     Hindered
    -0.08
    POSITIVE LOGITS
     steps
    0.36
     step
    0.29
     stages
    0.26
    æŃ¥
    0.26
    steps
    0.25
     stage
    0.24
     Steps
    0.24
    step
    0.22
    Steps
    0.21
    -step
    0.21
    Activations Density 0.028%

    No Known Activations