© 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. 55450
    Prev
    Next
    INDEX
    Explanations

    are vulnerable, those used, is stored

    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
    antro
    -0.09
    æķĪ
    -0.09
     Grove
    -0.09
     Walters
    -0.09
    oods
    -0.09
     anth
    -0.08
     Walt
    -0.08
     Crud
    -0.08
     æIJ
    -0.08
    èĻ
    -0.08
    POSITIVE LOGITS
     attack
    0.14
     Attack
    0.13
     Critical
    0.13
    Exposed
    0.13
     exposed
    0.12
    Attack
    0.12
    attack
    0.12
     critical
    0.12
     BY
    0.12
     sensitive
    0.11
    Activations Density 0.112%

    No Known Activations