© 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. 3563
    Prev
    Next
    INDEX
    Explanations

    how to use, pode utilizar

    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
     Harm
    -0.10
    uche
    -0.10
    rompt
    -0.09
     ï¾ĺ
    -0.09
    loit
    -0.09
     octave
    -0.09
    AtPath
    -0.09
     banner
    -0.09
     programs
    -0.08
    andas
    -0.08
    POSITIVE LOGITS
     razor
    0.12
     Slim
    0.11
    raz
    0.11
     slim
    0.11
    Slim
    0.10
     DI
    0.10
     config
    0.10
     Lever
    0.10
     route
    0.09
     define
    0.09
    Activations Density 0.236%

    No Known Activations