© 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. 58383
    Prev
    Next
    INDEX
    Explanations

    to avoid or evade

    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
    lian
    -0.10
    lazy
    -0.09
     Fantasy
    -0.09
     lazy
    -0.09
     overlook
    -0.08
    813
    -0.08
     forgetting
    -0.08
    _KeyPress
    -0.08
     grop
    -0.08
    WM
    -0.08
    POSITIVE LOGITS
     el
    0.38
     evade
    0.31
    éĢĥ
    0.29
     ev
    0.29
     escape
    0.28
     escaped
    0.25
     evasion
    0.25
     escapes
    0.24
     Escape
    0.23
    escape
    0.22
    Activations Density 0.063%

    No Known Activations