© 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. 62549
    Prev
    Next
    INDEX
    Explanations

    human knowledge and illegal things

    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
     جد
    -0.10
    çī¹èī²
    -0.09
     familiar
    -0.08
    ACL
    -0.08
     Intelligent
    -0.08
    itta
    -0.08
    pkt
    -0.08
    åĽº
    -0.08
    gles
    -0.08
    å°Ĭ
    -0.08
    POSITIVE LOGITS
     knowledge
    0.22
     Knowledge
    0.16
     everything
    0.14
     history
    0.14
    Knowledge
    0.14
    knowledge
    0.14
    çŁ¥è¯Ĩ
    0.13
    æīĢæľī
    0.13
     secrets
    0.13
     entire
    0.13
    Activations Density 0.190%

    No Known Activations