© 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. 25642
    Prev
    Next
    INDEX
    Explanations

    have a

    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
     itself
    -0.09
     coded
    -0.09
    -s
    -0.09
     Tam
    -0.08
    ä¹Ĥ
    -0.08
     purpose
    -0.08
    ize
    -0.08
     ade
    -0.08
     Gon
    -0.08
     ké
    -0.08
    POSITIVE LOGITS
     situation
    0.14
     дело
    0.14
     situations
    0.14
     two
    0.13
    å¦Ĥä¸ĭ
    0.12
     Situation
    0.11
     custody
    0.11
     following
    0.11
    two
    0.10
     access
    0.10
    Activations Density 0.101%

    No Known Activations