© 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. 21199
    Prev
    Next
    INDEX
    Explanations

    safety or injury

    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
    acr
    -0.11
     cracking
    -0.09
     corruption
    -0.09
    éĻµ
    -0.09
    âĢIJ'
    -0.09
     aire
    -0.09
     :.:
    -0.08
    GPS
    -0.08
     missed
    -0.08
     worm
    -0.08
    POSITIVE LOGITS
     machinery
    0.16
     Machinery
    0.14
     sharp
    0.13
    åį±
    0.12
     flying
    0.12
     electrical
    0.12
     dangerous
    0.12
    flamm
    0.12
    elect
    0.12
    danger
    0.11
    Activations Density 0.076%

    No Known Activations