© 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. 41085
    Prev
    Next
    INDEX
    Explanations

    methods of infiltration

    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
     addCriterion
    -0.09
     Wonderland
    -0.09
    æ¦
    -0.09
     extrad
    -0.09
     trapping
    -0.09
    ï¼ıï¼ı
    -0.09
     Brace
    -0.08
    eyJ
    -0.08
    onis
    -0.08
     ambush
    -0.08
    POSITIVE LOGITS
     scaling
    0.15
     Scaling
    0.14
     diversion
    0.14
     entry
    0.13
     gaining
    0.12
     gained
    0.12
    -disable
    0.12
     distract
    0.12
     минÑĥ
    0.12
    æ½ľ
    0.12
    Activations Density 0.053%

    No Known Activations