© 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. 15238
    Prev
    Next
    INDEX
    Explanations

    the object, the blood, his three

    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
     bru
    -0.11
    olis
    -0.11
    ä¸Ģ人
    -0.10
     trouble
    -0.10
     danger
    -0.10
     guarded
    -0.09
     riff
    -0.09
    ãĥŃãĥ³
    -0.09
    StackNavigator
    -0.09
     intim
    -0.08
    POSITIVE LOGITS
     constraints
    0.13
     unfamiliar
    0.13
    æĿŁ
    0.13
     bonds
    0.12
     ë¬
    0.10
     Laud
    0.10
    lest
    0.10
    w
    0.09
     seat
    0.09
     restrictions
    0.09
    Activations Density 0.047%

    No Known Activations