© 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. 37014
    Prev
    Next
    INDEX
    Explanations

    intricate designs

    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
     knit
    -0.12
     wrench
    -0.10
    ktop
    -0.10
     strapped
    -0.10
     Pow
    -0.09
    ä»ĭ
    -0.09
    blr
    -0.09
    verity
    -0.09
     fo
    -0.09
     Strap
    -0.09
    POSITIVE LOGITS
     thread
    0.34
     Thread
    0.27
    thread
    0.25
     threads
    0.24
     needle
    0.24
     needles
    0.22
    -thread
    0.21
    Thread
    0.21
    éĴĪ
    0.21
    _thread
    0.20
    Activations Density 0.053%

    No Known Activations