© 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. 29788
    Prev
    Next
    INDEX
    Explanations

    storytelling, games, children

    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
     technology
    -0.10
     Karlov
    -0.09
     shorts
    -0.09
     nid
    -0.09
     bufsize
    -0.08
     IT
    -0.08
    atk
    -0.08
    iscard
    -0.08
    gth
    -0.08
    Intialized
    -0.08
    POSITIVE LOGITS
    ＼＼
    0.09
     ãĢĢ
    0.09
     smart
    0.08
     amber
    0.08
    емо
    0.08
    Designer
    0.08
    ogan
    0.08
     outright
    0.08
    (Have
    0.08
    iterated
    0.08
    Activations Density 0.117%

    No Known Activations