© 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. 29531
    Prev
    Next
    INDEX
    Explanations

    handling chemicals and instructions

    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
    keterangan
    -0.11
    ingly
    -0.10
    ä¹Ĥ
    -0.10
     extrad
    -0.10
    å¼ı
    -0.09
    bac
    -0.09
    isse
    -0.09
     recep
    -0.09
     antib
    -0.08
     Provid
    -0.08
    POSITIVE LOGITS
     handling
    0.28
     handled
    0.24
     Handling
    0.24
     handle
    0.22
     Handle
    0.20
    Handling
    0.20
    handling
    0.19
     handles
    0.17
    -handle
    0.17
    åį±
    0.16
    Activations Density 0.054%

    No Known Activations