© 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. 60199
    Prev
    Next
    INDEX
    Explanations

    cutting metal pipes

    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
     Hava
    -0.09
    482
    -0.09
    ater
    -0.09
    atha
    -0.09
     unp
    -0.09
     @}
    -0.09
    ings
    -0.09
     pÅĤ
    -0.08
    iosa
    -0.08
    ilities
    -0.08
    POSITIVE LOGITS
    -edge
    0.19
     edge
    0.13
     cutting
    0.12
     Edge
    0.11
     Cutting
    0.11
    edge
    0.10
    lass
    0.10
    enuity
    0.10
    redient
    0.10
     down
    0.09
    Activations Density 0.007%

    No Known Activations